$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-Q6_K.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.097.891 I srv llama_server: initializing ... 0.00.097.898 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.098.015 I srv init_listene: The UI is disabled 0.00.098.018 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.098.151 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.110.202 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-Q6_K.gguf' 0.02.919.368 I cmn init: llama threadpool init, n_threads = 8 0.02.993.713 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.998.427 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.998.445 I srv llama_server: model loaded 0.02.998.448 I srv llama_server: listening on http://127.0.0.1:8089 0.04.521.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.521.396 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.419.469 I slot print_timing: id 0 | task 0 | prompt eval time = 114.87 ms / 368 tokens ( 0.31 ms per token, 3203.51 tokens per second) 0.05.419.475 I slot print_timing: id 0 | task 0 | eval time = 783.18 ms / 61 tokens ( 13.05 ms per token, 76.61 tokens per second) 0.05.419.476 I slot print_timing: id 0 | task 0 | total time = 898.06 ms / 429 tokens 0.05.419.482 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.05.419.483 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.419.513 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.05.439.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 5323680 0.05.454.658 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.06.104.916 I slot print_timing: id 0 | task 62 | prompt eval time = 90.82 ms / 292 tokens ( 0.31 ms per token, 3215.04 tokens per second) 0.06.104.922 I slot print_timing: id 0 | task 62 | eval time = 559.42 ms / 44 tokens ( 13.01 ms per token, 76.87 tokens per second) 0.06.104.923 I slot print_timing: id 0 | task 62 | total time = 650.24 ms / 336 tokens 0.06.104.923 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.06.104.924 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.104.948 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.06.128.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 6009115 0.06.140.596 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.06.814.219 I slot print_timing: id 0 | task 107 | prompt eval time = 101.26 ms / 338 tokens ( 0.30 ms per token, 3337.88 tokens per second) 0.06.814.225 I slot print_timing: id 0 | task 107 | eval time = 572.35 ms / 45 tokens ( 13.01 ms per token, 76.88 tokens per second) 0.06.814.226 I slot print_timing: id 0 | task 107 | total time = 673.61 ms / 383 tokens 0.06.814.227 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.06.814.227 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.814.256 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.06.833.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 6718423 0.06.847.917 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.07.533.814 I slot print_timing: id 0 | task 153 | prompt eval time = 100.84 ms / 371 tokens ( 0.27 ms per token, 3679.10 tokens per second) 0.07.533.820 I slot print_timing: id 0 | task 153 | eval time = 585.04 ms / 46 tokens ( 13.00 ms per token, 76.92 tokens per second) 0.07.533.821 I slot print_timing: id 0 | task 153 | total time = 685.88 ms / 417 tokens 0.07.533.822 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.07.533.823 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.533.852 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.07.548.783 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.091 0.07.563.827 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.08.444.609 I slot print_timing: id 0 | task 200 | prompt eval time = 101.22 ms / 345 tokens ( 0.29 ms per token, 3408.52 tokens per second) 0.08.444.614 I slot print_timing: id 0 | task 200 | eval time = 779.55 ms / 61 tokens ( 12.99 ms per token, 76.97 tokens per second) 0.08.444.615 I slot print_timing: id 0 | task 200 | total time = 880.77 ms / 406 tokens 0.08.444.616 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.08.444.617 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.444.644 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.08.468.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 8348811 0.08.483.938 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.09.403.658 I slot print_timing: id 0 | task 262 | prompt eval time = 100.97 ms / 351 tokens ( 0.29 ms per token, 3476.25 tokens per second) 0.09.403.665 I slot print_timing: id 0 | task 262 | eval time = 818.73 ms / 64 tokens ( 13.00 ms per token, 76.95 tokens per second) 0.09.403.666 I slot print_timing: id 0 | task 262 | total time = 919.70 ms / 415 tokens 0.09.403.667 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.09.403.668 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.403.698 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.09.423.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 9307864 0.09.439.169 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.10.584.502 I slot print_timing: id 0 | task 327 | prompt eval time = 123.14 ms / 395 tokens ( 0.31 ms per token, 3207.60 tokens per second) 0.10.584.508 I slot print_timing: id 0 | task 327 | eval time = 1022.17 ms / 79 tokens ( 13.10 ms per token, 76.31 tokens per second) 0.10.584.509 I slot print_timing: id 0 | task 327 | total time = 1145.32 ms / 474 tokens 0.10.584.510 I slot print_timing: id 0 | task 327 | graphs reused = 387 0.10.584.510 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.584.540 I slot release: id 0 | task 327 | stop processing: n_tokens = 498, truncated = 0 0.10.589.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 10488707 0.10.606.008 I slot launch_slot_: id 0 | task 407 | processing task, is_child = 0 0.11.659.734 I slot print_timing: id 0 | task 407 | prompt eval time = 125.60 ms / 446 tokens ( 0.28 ms per token, 3551.01 tokens per second) 0.11.659.740 I slot print_timing: id 0 | task 407 | eval time = 928.11 ms / 72 tokens ( 13.07 ms per token, 76.50 tokens per second) 0.11.659.741 I slot print_timing: id 0 | task 407 | total time = 1053.71 ms / 518 tokens 0.11.659.742 I slot print_timing: id 0 | task 407 | graphs reused = 456 0.11.659.743 I slot print_timing: id 0 | task 407 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.659.774 I slot release: id 0 | task 407 | stop processing: n_tokens = 542, truncated = 0 0.11.686.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 11563941 0.11.705.129 I slot launch_slot_: id 0 | task 480 | processing task, is_child = 0 0.12.458.503 I slot print_timing: id 0 | task 480 | prompt eval time = 91.29 ms / 319 tokens ( 0.29 ms per token, 3494.40 tokens per second) 0.12.458.509 I slot print_timing: id 0 | task 480 | eval time = 662.07 ms / 52 tokens ( 12.98 ms per token, 77.03 tokens per second) 0.12.458.510 I slot print_timing: id 0 | task 480 | total time = 753.36 ms / 371 tokens 0.12.458.511 I slot print_timing: id 0 | task 480 | graphs reused = 506 0.12.458.512 I slot print_timing: id 0 | task 480 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.458.540 I slot release: id 0 | task 480 | stop processing: n_tokens = 395, truncated = 0 0.12.480.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 12362707 0.12.494.754 I slot launch_slot_: id 0 | task 533 | processing task, is_child = 0 0.13.120.828 I slot print_timing: id 0 | task 533 | prompt eval time = 92.31 ms / 336 tokens ( 0.27 ms per token, 3639.79 tokens per second) 0.13.120.833 I slot print_timing: id 0 | task 533 | eval time = 533.74 ms / 42 tokens ( 13.02 ms per token, 76.82 tokens per second) 0.13.120.834 I slot print_timing: id 0 | task 533 | total time = 626.06 ms / 378 tokens 0.13.120.835 I slot print_timing: id 0 | task 533 | graphs reused = 546 0.13.120.836 I slot print_timing: id 0 | task 533 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.120.865 I slot release: id 0 | task 533 | stop processing: n_tokens = 402, truncated = 0 0.13.136.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 13025032 0.13.150.472 I slot launch_slot_: id 0 | task 576 | processing task, is_child = 0 0.14.129.821 I slot print_timing: id 0 | task 576 | prompt eval time = 101.16 ms / 352 tokens ( 0.29 ms per token, 3479.53 tokens per second) 0.14.129.826 I slot print_timing: id 0 | task 576 | eval time = 878.17 ms / 68 tokens ( 13.11 ms per token, 76.29 tokens per second) 0.14.129.827 I slot print_timing: id 0 | task 576 | total time = 979.33 ms / 420 tokens 0.14.129.828 I slot print_timing: id 0 | task 576 | graphs reused = 612 0.14.129.829 I slot print_timing: id 0 | task 576 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.129.856 I slot release: id 0 | task 576 | stop processing: n_tokens = 444, truncated = 0 0.14.147.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 14034023 0.14.162.739 I slot launch_slot_: id 0 | task 645 | processing task, is_child = 0 0.14.948.482 I slot print_timing: id 0 | task 645 | prompt eval time = 123.20 ms / 387 tokens ( 0.32 ms per token, 3141.13 tokens per second) 0.14.948.487 I slot print_timing: id 0 | task 645 | eval time = 662.52 ms / 52 tokens ( 12.99 ms per token, 76.98 tokens per second) 0.14.948.488 I slot print_timing: id 0 | task 645 | total time = 785.73 ms / 439 tokens 0.14.948.489 I slot print_timing: id 0 | task 645 | graphs reused = 662 0.14.948.490 I slot print_timing: id 0 | task 645 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.948.521 I slot release: id 0 | task 645 | stop processing: n_tokens = 463, truncated = 0 0.14.974.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 14852688 0.14.989.943 I slot launch_slot_: id 0 | task 698 | processing task, is_child = 0 0.15.909.196 I slot print_timing: id 0 | task 698 | prompt eval time = 100.94 ms / 349 tokens ( 0.29 ms per token, 3457.64 tokens per second) 0.15.909.202 I slot print_timing: id 0 | task 698 | eval time = 818.30 ms / 64 tokens ( 12.99 ms per token, 76.99 tokens per second) 0.15.909.204 I slot print_timing: id 0 | task 698 | total time = 919.24 ms / 413 tokens 0.15.909.205 I slot print_timing: id 0 | task 698 | graphs reused = 724 0.15.909.206 I slot print_timing: id 0 | task 698 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.909.237 I slot release: id 0 | task 698 | stop processing: n_tokens = 437, truncated = 0 0.15.933.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 15813403 0.15.947.841 I slot launch_slot_: id 0 | task 763 | processing task, is_child = 0 0.16.793.718 I slot print_timing: id 0 | task 763 | prompt eval time = 101.20 ms / 352 tokens ( 0.29 ms per token, 3478.23 tokens per second) 0.16.793.724 I slot print_timing: id 0 | task 763 | eval time = 744.66 ms / 57 tokens ( 13.30 ms per token, 75.20 tokens per second) 0.16.793.725 I slot print_timing: id 0 | task 763 | total time = 845.86 ms / 409 tokens 0.16.793.725 I slot print_timing: id 0 | task 763 | graphs reused = 779 0.16.793.726 I slot print_timing: id 0 | task 763 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.793.755 I slot release: id 0 | task 763 | stop processing: n_tokens = 433, truncated = 0 0.16.797.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 16697922 0.16.812.695 I slot launch_slot_: id 0 | task 821 | processing task, is_child = 0 0.17.792.813 I slot print_timing: id 0 | task 821 | prompt eval time = 101.89 ms / 347 tokens ( 0.29 ms per token, 3405.57 tokens per second) 0.17.792.819 I slot print_timing: id 0 | task 821 | eval time = 878.21 ms / 68 tokens ( 13.11 ms per token, 76.29 tokens per second) 0.17.792.820 I slot print_timing: id 0 | task 821 | total time = 980.10 ms / 415 tokens 0.17.792.821 I slot print_timing: id 0 | task 821 | graphs reused = 845 0.17.792.822 I slot print_timing: id 0 | task 821 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.792.848 I slot release: id 0 | task 821 | stop processing: n_tokens = 439, truncated = 0 0.17.815.008 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 17697015 0.17.829.796 I slot launch_slot_: id 0 | task 890 | processing task, is_child = 0 0.18.635.890 I slot print_timing: id 0 | task 890 | prompt eval time = 91.70 ms / 320 tokens ( 0.29 ms per token, 3489.79 tokens per second) 0.18.635.896 I slot print_timing: id 0 | task 890 | eval time = 714.38 ms / 56 tokens ( 12.99 ms per token, 76.99 tokens per second) 0.18.635.897 I slot print_timing: id 0 | task 890 | total time = 806.08 ms / 376 tokens 0.18.635.898 I slot print_timing: id 0 | task 890 | graphs reused = 899 0.18.635.900 I slot print_timing: id 0 | task 890 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.635.927 I slot release: id 0 | task 890 | stop processing: n_tokens = 400, truncated = 0 0.18.640.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 18540094 0.18.654.267 I slot launch_slot_: id 0 | task 947 | processing task, is_child = 0 0.19.314.987 I slot print_timing: id 0 | task 947 | prompt eval time = 101.10 ms / 343 tokens ( 0.29 ms per token, 3392.81 tokens per second) 0.19.314.993 I slot print_timing: id 0 | task 947 | eval time = 559.61 ms / 44 tokens ( 13.01 ms per token, 76.84 tokens per second) 0.19.314.994 I slot print_timing: id 0 | task 947 | total time = 660.71 ms / 387 tokens 0.19.314.995 I slot print_timing: id 0 | task 947 | graphs reused = 941 0.19.314.995 I slot print_timing: id 0 | task 947 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.315.022 I slot release: id 0 | task 947 | stop processing: n_tokens = 411, truncated = 0 0.19.340.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 19219189 0.19.355.141 I slot launch_slot_: id 0 | task 992 | processing task, is_child = 0 0.20.006.097 I slot print_timing: id 0 | task 992 | prompt eval time = 91.60 ms / 325 tokens ( 0.28 ms per token, 3548.00 tokens per second) 0.20.006.102 I slot print_timing: id 0 | task 992 | eval time = 559.34 ms / 44 tokens ( 13.01 ms per token, 76.88 tokens per second) 0.20.006.104 I slot print_timing: id 0 | task 992 | total time = 650.94 ms / 369 tokens 0.20.006.104 I slot print_timing: id 0 | task 992 | graphs reused = 983 0.20.006.105 I slot print_timing: id 0 | task 992 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.006.137 I slot release: id 0 | task 992 | stop processing: n_tokens = 393, truncated = 0 0.20.024.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 19910304 0.20.038.411 I slot launch_slot_: id 0 | task 1037 | processing task, is_child = 0 0.20.676.624 I slot print_timing: id 0 | task 1037 | prompt eval time = 91.84 ms / 323 tokens ( 0.28 ms per token, 3516.87 tokens per second) 0.20.676.630 I slot print_timing: id 0 | task 1037 | eval time = 546.35 ms / 43 tokens ( 13.01 ms per token, 76.87 tokens per second) 0.20.676.631 I slot print_timing: id 0 | task 1037 | total time = 638.20 ms / 366 tokens 0.20.676.632 I slot print_timing: id 0 | task 1037 | graphs reused = 1024 0.20.676.633 I slot print_timing: id 0 | task 1037 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.676.661 I slot release: id 0 | task 1037 | stop processing: n_tokens = 390, truncated = 0 0.20.699.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 20580827 0.20.713.384 I slot launch_slot_: id 0 | task 1081 | processing task, is_child = 0 0.21.724.597 I slot print_timing: id 0 | task 1081 | prompt eval time = 101.25 ms / 359 tokens ( 0.28 ms per token, 3545.85 tokens per second) 0.21.724.602 I slot print_timing: id 0 | task 1081 | eval time = 909.95 ms / 69 tokens ( 13.38 ms per token, 74.73 tokens per second) 0.21.724.604 I slot print_timing: id 0 | task 1081 | total time = 1011.20 ms / 428 tokens 0.21.724.604 I slot print_timing: id 0 | task 1081 | graphs reused = 1091 0.21.724.605 I slot print_timing: id 0 | task 1081 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.724.634 I slot release: id 0 | task 1081 | stop processing: n_tokens = 452, truncated = 0 0.21.741.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 21628800 0.21.756.634 I slot launch_slot_: id 0 | task 1151 | processing task, is_child = 0 0.22.654.002 I slot print_timing: id 0 | task 1151 | prompt eval time = 92.07 ms / 334 tokens ( 0.28 ms per token, 3627.52 tokens per second) 0.22.654.009 I slot print_timing: id 0 | task 1151 | eval time = 805.28 ms / 63 tokens ( 12.99 ms per token, 76.99 tokens per second) 0.22.654.010 I slot print_timing: id 0 | task 1151 | total time = 897.35 ms / 397 tokens 0.22.654.011 I slot print_timing: id 0 | task 1151 | graphs reused = 1152 0.22.654.012 I slot print_timing: id 0 | task 1151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.654.044 I slot release: id 0 | task 1151 | stop processing: n_tokens = 421, truncated = 0 0.22.676.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 22558211 0.22.691.569 I slot launch_slot_: id 0 | task 1215 | processing task, is_child = 0 0.23.726.635 I slot print_timing: id 0 | task 1215 | prompt eval time = 101.04 ms / 382 tokens ( 0.26 ms per token, 3780.61 tokens per second) 0.23.726.642 I slot print_timing: id 0 | task 1215 | eval time = 934.01 ms / 73 tokens ( 12.97 ms per token, 77.09 tokens per second) 0.23.726.643 I slot print_timing: id 0 | task 1215 | total time = 1035.05 ms / 455 tokens 0.23.726.644 I slot print_timing: id 0 | task 1215 | graphs reused = 1223 0.23.726.645 I slot print_timing: id 0 | task 1215 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.726.677 I slot release: id 0 | task 1215 | stop processing: n_tokens = 479, truncated = 0 0.23.749.074 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 23630844 0.23.765.421 I slot launch_slot_: id 0 | task 1289 | processing task, is_child = 0 0.24.697.322 I slot print_timing: id 0 | task 1289 | prompt eval time = 101.74 ms / 368 tokens ( 0.28 ms per token, 3617.17 tokens per second) 0.24.697.328 I slot print_timing: id 0 | task 1289 | eval time = 830.14 ms / 65 tokens ( 12.97 ms per token, 77.10 tokens per second) 0.24.697.329 I slot print_timing: id 0 | task 1289 | total time = 931.88 ms / 433 tokens 0.24.697.330 I slot print_timing: id 0 | task 1289 | graphs reused = 1286 0.24.697.331 I slot print_timing: id 0 | task 1289 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.697.360 I slot release: id 0 | task 1289 | stop processing: n_tokens = 457, truncated = 0 0.24.718.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 24601527 0.24.733.562 I slot launch_slot_: id 0 | task 1355 | processing task, is_child = 0 0.25.949.646 I slot print_timing: id 0 | task 1355 | prompt eval time = 101.58 ms / 382 tokens ( 0.27 ms per token, 3760.43 tokens per second) 0.25.949.651 I slot print_timing: id 0 | task 1355 | eval time = 1114.48 ms / 87 tokens ( 12.96 ms per token, 77.17 tokens per second) 0.25.949.652 I slot print_timing: id 0 | task 1355 | total time = 1216.07 ms / 469 tokens 0.25.949.653 I slot print_timing: id 0 | task 1355 | graphs reused = 1371 0.25.949.654 I slot print_timing: id 0 | task 1355 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.949.683 I slot release: id 0 | task 1355 | stop processing: n_tokens = 493, truncated = 0 0.25.954.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 25853850 0.25.970.657 I slot launch_slot_: id 0 | task 1443 | processing task, is_child = 0 0.26.951.797 I slot print_timing: id 0 | task 1443 | prompt eval time = 124.40 ms / 410 tokens ( 0.30 ms per token, 3295.93 tokens per second) 0.26.951.803 I slot print_timing: id 0 | task 1443 | eval time = 856.73 ms / 67 tokens ( 12.98 ms per token, 77.04 tokens per second) 0.26.951.805 I slot print_timing: id 0 | task 1443 | total time = 981.13 ms / 477 tokens 0.26.951.805 I slot print_timing: id 0 | task 1443 | graphs reused = 1436 0.26.951.806 I slot print_timing: id 0 | task 1443 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.951.835 I slot release: id 0 | task 1443 | stop processing: n_tokens = 501, truncated = 0 0.26.978.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 26856002 0.26.995.522 I slot launch_slot_: id 0 | task 1511 | processing task, is_child = 0 0.27.926.856 I slot print_timing: id 0 | task 1511 | prompt eval time = 101.58 ms / 367 tokens ( 0.28 ms per token, 3612.81 tokens per second) 0.27.926.861 I slot print_timing: id 0 | task 1511 | eval time = 829.74 ms / 65 tokens ( 12.96 ms per token, 77.13 tokens per second) 0.27.926.863 I slot print_timing: id 0 | task 1511 | total time = 931.32 ms / 432 tokens 0.27.926.863 I slot print_timing: id 0 | task 1511 | graphs reused = 1499 0.27.926.864 I slot print_timing: id 0 | task 1511 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.926.893 I slot release: id 0 | task 1511 | stop processing: n_tokens = 458, truncated = 0 0.27.954.656 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 27831060 0.27.970.375 I slot launch_slot_: id 0 | task 1577 | processing task, is_child = 0 0.28.750.222 I slot print_timing: id 0 | task 1577 | prompt eval time = 91.87 ms / 326 tokens ( 0.28 ms per token, 3548.49 tokens per second) 0.28.750.227 I slot print_timing: id 0 | task 1577 | eval time = 687.96 ms / 54 tokens ( 12.98 ms per token, 77.04 tokens per second) 0.28.750.228 I slot print_timing: id 0 | task 1577 | total time = 779.83 ms / 380 tokens 0.28.750.229 I slot print_timing: id 0 | task 1577 | graphs reused = 1551 0.28.750.230 I slot print_timing: id 0 | task 1577 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.750.259 I slot release: id 0 | task 1577 | stop processing: n_tokens = 404, truncated = 0 0.28.764.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 28654425 0.28.777.749 I slot launch_slot_: id 0 | task 1632 | processing task, is_child = 0 0.29.696.814 I slot print_timing: id 0 | task 1632 | prompt eval time = 101.48 ms / 351 tokens ( 0.29 ms per token, 3458.78 tokens per second) 0.29.696.820 I slot print_timing: id 0 | task 1632 | eval time = 817.57 ms / 64 tokens ( 12.98 ms per token, 77.06 tokens per second) 0.29.696.821 I slot print_timing: id 0 | task 1632 | total time = 919.05 ms / 415 tokens 0.29.696.821 I slot print_timing: id 0 | task 1632 | graphs reused = 1613 0.29.696.822 I slot print_timing: id 0 | task 1632 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.696.852 I slot release: id 0 | task 1632 | stop processing: n_tokens = 441, truncated = 0 0.29.701.215 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 29601019 0.29.716.308 I slot launch_slot_: id 0 | task 1697 | processing task, is_child = 0 0.30.826.368 I slot print_timing: id 0 | task 1697 | prompt eval time = 101.68 ms / 379 tokens ( 0.27 ms per token, 3727.34 tokens per second) 0.30.826.373 I slot print_timing: id 0 | task 1697 | eval time = 1008.36 ms / 78 tokens ( 13.10 ms per token, 76.36 tokens per second) 0.30.826.374 I slot print_timing: id 0 | task 1697 | total time = 1110.04 ms / 457 tokens 0.30.826.375 I slot print_timing: id 0 | task 1697 | graphs reused = 1689 0.30.826.376 I slot print_timing: id 0 | task 1697 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.826.405 I slot release: id 0 | task 1697 | stop processing: n_tokens = 481, truncated = 0 0.30.839.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 30730572 0.30.856.281 I slot launch_slot_: id 0 | task 1776 | processing task, is_child = 0 0.31.863.666 I slot print_timing: id 0 | task 1776 | prompt eval time = 101.67 ms / 356 tokens ( 0.29 ms per token, 3501.46 tokens per second) 0.31.863.671 I slot print_timing: id 0 | task 1776 | eval time = 905.70 ms / 70 tokens ( 13.13 ms per token, 76.18 tokens per second) 0.31.863.673 I slot print_timing: id 0 | task 1776 | total time = 1007.37 ms / 426 tokens 0.31.863.673 I slot print_timing: id 0 | task 1776 | graphs reused = 1757 0.31.863.674 I slot print_timing: id 0 | task 1776 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.863.703 I slot release: id 0 | task 1776 | stop processing: n_tokens = 450, truncated = 0 0.31.884.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 31767870 0.31.899.976 I slot launch_slot_: id 0 | task 1847 | processing task, is_child = 0 0.32.771.819 I slot print_timing: id 0 | task 1847 | prompt eval time = 91.96 ms / 331 tokens ( 0.28 ms per token, 3599.39 tokens per second) 0.32.771.825 I slot print_timing: id 0 | task 1847 | eval time = 779.87 ms / 61 tokens ( 13.00 ms per token, 76.94 tokens per second) 0.32.771.826 I slot print_timing: id 0 | task 1847 | total time = 871.83 ms / 392 tokens 0.32.771.827 I slot print_timing: id 0 | task 1847 | graphs reused = 1816 0.32.771.828 I slot print_timing: id 0 | task 1847 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.771.856 I slot release: id 0 | task 1847 | stop processing: n_tokens = 416, truncated = 0 0.32.798.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 32676023 0.32.813.622 I slot launch_slot_: id 0 | task 1909 | processing task, is_child = 0 0.33.345.799 I slot print_timing: id 0 | task 1909 | prompt eval time = 92.25 ms / 334 tokens ( 0.28 ms per token, 3620.79 tokens per second) 0.33.345.805 I slot print_timing: id 0 | task 1909 | eval time = 439.92 ms / 34 tokens ( 13.33 ms per token, 75.01 tokens per second) 0.33.345.806 I slot print_timing: id 0 | task 1909 | total time = 532.16 ms / 368 tokens 0.33.345.807 I slot print_timing: id 0 | task 1909 | graphs reused = 1848 0.33.345.808 I slot print_timing: id 0 | task 1909 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.345.835 I slot release: id 0 | task 1909 | stop processing: n_tokens = 392, truncated = 0 0.33.350.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 33250002 0.33.363.743 I slot launch_slot_: id 0 | task 1944 | processing task, is_child = 0 0.34.336.341 I slot print_timing: id 0 | task 1944 | prompt eval time = 102.14 ms / 362 tokens ( 0.28 ms per token, 3544.09 tokens per second) 0.34.336.347 I slot print_timing: id 0 | task 1944 | eval time = 870.44 ms / 68 tokens ( 12.99 ms per token, 76.97 tokens per second) 0.34.336.348 I slot print_timing: id 0 | task 1944 | total time = 972.58 ms / 430 tokens 0.34.336.349 I slot print_timing: id 0 | task 1944 | graphs reused = 1914 0.34.336.350 I slot print_timing: id 0 | task 1944 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.336.380 I slot release: id 0 | task 1944 | stop processing: n_tokens = 454, truncated = 0 0.34.361.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 34240547 0.34.376.592 I slot launch_slot_: id 0 | task 2013 | processing task, is_child = 0 0.35.321.990 I slot print_timing: id 0 | task 2013 | prompt eval time = 101.58 ms / 384 tokens ( 0.26 ms per token, 3780.46 tokens per second) 0.35.321.995 I slot print_timing: id 0 | task 2013 | eval time = 843.81 ms / 66 tokens ( 12.98 ms per token, 77.03 tokens per second) 0.35.321.996 I slot print_timing: id 0 | task 2013 | total time = 945.38 ms / 450 tokens 0.35.321.997 I slot print_timing: id 0 | task 2013 | graphs reused = 1978 0.35.321.998 I slot print_timing: id 0 | task 2013 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.322.028 I slot release: id 0 | task 2013 | stop processing: n_tokens = 474, truncated = 0 0.35.346.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 35226195 0.35.362.807 I slot launch_slot_: id 0 | task 2080 | processing task, is_child = 0 0.36.156.032 I slot print_timing: id 0 | task 2080 | prompt eval time = 91.83 ms / 325 tokens ( 0.28 ms per token, 3539.19 tokens per second) 0.36.156.037 I slot print_timing: id 0 | task 2080 | eval time = 701.38 ms / 55 tokens ( 12.99 ms per token, 76.99 tokens per second) 0.36.156.039 I slot print_timing: id 0 | task 2080 | total time = 793.21 ms / 380 tokens 0.36.156.039 I slot print_timing: id 0 | task 2080 | graphs reused = 2031 0.36.156.040 I slot print_timing: id 0 | task 2080 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.156.068 I slot release: id 0 | task 2080 | stop processing: n_tokens = 404, truncated = 0 0.36.179.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 36060234 0.36.193.090 I slot launch_slot_: id 0 | task 2136 | processing task, is_child = 0 0.37.057.818 I slot print_timing: id 0 | task 2136 | prompt eval time = 101.86 ms / 366 tokens ( 0.28 ms per token, 3593.17 tokens per second) 0.37.057.823 I slot print_timing: id 0 | task 2136 | eval time = 762.85 ms / 59 tokens ( 13.15 ms per token, 76.03 tokens per second) 0.37.057.824 I slot print_timing: id 0 | task 2136 | total time = 864.71 ms / 425 tokens 0.37.057.825 I slot print_timing: id 0 | task 2136 | graphs reused = 2088 0.37.057.826 I slot print_timing: id 0 | task 2136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.057.862 I slot release: id 0 | task 2136 | stop processing: n_tokens = 449, truncated = 0 0.37.087.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 36962029 0.37.102.401 I slot launch_slot_: id 0 | task 2196 | processing task, is_child = 0 0.37.650.943 I slot print_timing: id 0 | task 2196 | prompt eval time = 91.02 ms / 295 tokens ( 0.31 ms per token, 3240.94 tokens per second) 0.37.650.950 I slot print_timing: id 0 | task 2196 | eval time = 457.50 ms / 36 tokens ( 13.07 ms per token, 76.50 tokens per second) 0.37.650.951 I slot print_timing: id 0 | task 2196 | total time = 548.52 ms / 331 tokens 0.37.650.952 I slot print_timing: id 0 | task 2196 | graphs reused = 2122 0.37.650.953 I slot print_timing: id 0 | task 2196 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.650.982 I slot release: id 0 | task 2196 | stop processing: n_tokens = 355, truncated = 0 0.37.679.226 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 37555149 0.37.692.188 I slot launch_slot_: id 0 | task 2233 | processing task, is_child = 0 0.38.433.468 I slot print_timing: id 0 | task 2233 | prompt eval time = 91.18 ms / 307 tokens ( 0.30 ms per token, 3366.89 tokens per second) 0.38.433.474 I slot print_timing: id 0 | task 2233 | eval time = 650.08 ms / 50 tokens ( 13.27 ms per token, 75.38 tokens per second) 0.38.433.475 I slot print_timing: id 0 | task 2233 | total time = 741.26 ms / 357 tokens 0.38.433.476 I slot print_timing: id 0 | task 2233 | graphs reused = 2170 0.38.433.477 I slot print_timing: id 0 | task 2233 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.433.503 I slot release: id 0 | task 2233 | stop processing: n_tokens = 381, truncated = 0 0.38.437.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 38337670 0.38.450.931 I slot launch_slot_: id 0 | task 2284 | processing task, is_child = 0 0.39.025.360 I slot print_timing: id 0 | task 2284 | prompt eval time = 92.14 ms / 319 tokens ( 0.29 ms per token, 3462.20 tokens per second) 0.39.025.366 I slot print_timing: id 0 | task 2284 | eval time = 482.28 ms / 38 tokens ( 13.03 ms per token, 76.72 tokens per second) 0.39.025.367 I slot print_timing: id 0 | task 2284 | total time = 574.41 ms / 357 tokens 0.39.025.368 I slot print_timing: id 0 | task 2284 | graphs reused = 2206 0.39.025.369 I slot print_timing: id 0 | task 2284 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.025.396 I slot release: id 0 | task 2284 | stop processing: n_tokens = 381, truncated = 0 0.39.043.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 38929563 0.39.056.318 I slot launch_slot_: id 0 | task 2323 | processing task, is_child = 0 0.39.823.831 I slot print_timing: id 0 | task 2323 | prompt eval time = 91.81 ms / 315 tokens ( 0.29 ms per token, 3430.89 tokens per second) 0.39.823.836 I slot print_timing: id 0 | task 2323 | eval time = 675.68 ms / 53 tokens ( 12.99 ms per token, 76.96 tokens per second) 0.39.823.837 I slot print_timing: id 0 | task 2323 | total time = 767.50 ms / 368 tokens 0.39.823.838 I slot print_timing: id 0 | task 2323 | graphs reused = 2257 0.39.823.839 I slot print_timing: id 0 | task 2323 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.823.866 I slot release: id 0 | task 2323 | stop processing: n_tokens = 392, truncated = 0 0.39.850.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 39728033 0.39.864.362 I slot launch_slot_: id 0 | task 2377 | processing task, is_child = 0 0.40.705.675 I slot print_timing: id 0 | task 2377 | prompt eval time = 101.99 ms / 367 tokens ( 0.28 ms per token, 3598.39 tokens per second) 0.40.705.680 I slot print_timing: id 0 | task 2377 | eval time = 739.31 ms / 58 tokens ( 12.97 ms per token, 77.10 tokens per second) 0.40.705.681 I slot print_timing: id 0 | task 2377 | total time = 841.30 ms / 425 tokens 0.40.705.682 I slot print_timing: id 0 | task 2377 | graphs reused = 2313 0.40.705.683 I slot print_timing: id 0 | task 2377 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.705.712 I slot release: id 0 | task 2377 | stop processing: n_tokens = 449, truncated = 0 0.40.727.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 40609879 0.40.742.548 I slot launch_slot_: id 0 | task 2436 | processing task, is_child = 0 0.41.809.730 I slot print_timing: id 0 | task 2436 | prompt eval time = 141.16 ms / 499 tokens ( 0.28 ms per token, 3535.05 tokens per second) 0.41.809.735 I slot print_timing: id 0 | task 2436 | eval time = 926.01 ms / 70 tokens ( 13.42 ms per token, 74.51 tokens per second) 0.41.809.736 I slot print_timing: id 0 | task 2436 | total time = 1067.17 ms / 569 tokens 0.41.809.737 I slot print_timing: id 0 | task 2436 | graphs reused = 2381 0.41.809.738 I slot print_timing: id 0 | task 2436 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.809.770 I slot release: id 0 | task 2436 | stop processing: n_tokens = 593, truncated = 0 0.41.826.362 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 41713937 0.41.845.311 I slot launch_slot_: id 0 | task 2507 | processing task, is_child = 0 0.42.572.824 I slot print_timing: id 0 | task 2507 | prompt eval time = 91.43 ms / 319 tokens ( 0.29 ms per token, 3489.08 tokens per second) 0.42.572.829 I slot print_timing: id 0 | task 2507 | eval time = 636.07 ms / 50 tokens ( 12.98 ms per token, 77.04 tokens per second) 0.42.572.830 I slot print_timing: id 0 | task 2507 | total time = 727.50 ms / 369 tokens 0.42.572.831 I slot print_timing: id 0 | task 2507 | graphs reused = 2429 0.42.572.832 I slot print_timing: id 0 | task 2507 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.572.860 I slot release: id 0 | task 2507 | stop processing: n_tokens = 393, truncated = 0 0.42.593.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 42477027 0.42.606.952 I slot launch_slot_: id 0 | task 2558 | processing task, is_child = 0 0.43.447.855 I slot print_timing: id 0 | task 2558 | prompt eval time = 101.39 ms / 348 tokens ( 0.29 ms per token, 3432.36 tokens per second) 0.43.447.861 I slot print_timing: id 0 | task 2558 | eval time = 739.50 ms / 58 tokens ( 12.97 ms per token, 77.08 tokens per second) 0.43.447.862 I slot print_timing: id 0 | task 2558 | total time = 840.89 ms / 406 tokens 0.43.447.863 I slot print_timing: id 0 | task 2558 | graphs reused = 2485 0.43.447.864 I slot print_timing: id 0 | task 2558 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.447.894 I slot release: id 0 | task 2558 | stop processing: n_tokens = 430, truncated = 0 0.43.452.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 43352061 0.43.467.478 I slot launch_slot_: id 0 | task 2617 | processing task, is_child = 0 0.44.558.854 I slot print_timing: id 0 | task 2617 | prompt eval time = 124.29 ms / 404 tokens ( 0.31 ms per token, 3250.51 tokens per second) 0.44.558.860 I slot print_timing: id 0 | task 2617 | eval time = 967.07 ms / 75 tokens ( 13.07 ms per token, 76.52 tokens per second) 0.44.558.861 I slot print_timing: id 0 | task 2617 | total time = 1091.36 ms / 479 tokens 0.44.558.862 I slot print_timing: id 0 | task 2617 | graphs reused = 2558 0.44.558.864 I slot print_timing: id 0 | task 2617 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.558.893 I slot release: id 0 | task 2617 | stop processing: n_tokens = 503, truncated = 0 0.44.563.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 44463060 0.44.580.296 I slot launch_slot_: id 0 | task 2693 | processing task, is_child = 0 0.45.480.403 I slot print_timing: id 0 | task 2693 | prompt eval time = 124.44 ms / 408 tokens ( 0.31 ms per token, 3278.61 tokens per second) 0.45.480.409 I slot print_timing: id 0 | task 2693 | eval time = 775.65 ms / 60 tokens ( 13.15 ms per token, 76.07 tokens per second) 0.45.480.410 I slot print_timing: id 0 | task 2693 | total time = 900.09 ms / 468 tokens 0.45.480.411 I slot print_timing: id 0 | task 2693 | graphs reused = 2616 0.45.480.412 I slot print_timing: id 0 | task 2693 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.480.444 I slot release: id 0 | task 2693 | stop processing: n_tokens = 494, truncated = 0 0.45.484.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 45384611 0.45.501.327 I slot launch_slot_: id 0 | task 2754 | processing task, is_child = 0 0.46.224.808 I slot print_timing: id 0 | task 2754 | prompt eval time = 92.01 ms / 325 tokens ( 0.28 ms per token, 3532.22 tokens per second) 0.46.224.813 I slot print_timing: id 0 | task 2754 | eval time = 631.45 ms / 49 tokens ( 13.16 ms per token, 76.02 tokens per second) 0.46.224.814 I slot print_timing: id 0 | task 2754 | total time = 723.46 ms / 374 tokens 0.46.224.815 I slot print_timing: id 0 | task 2754 | graphs reused = 2663 0.46.224.816 I slot print_timing: id 0 | task 2754 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.224.844 I slot release: id 0 | task 2754 | stop processing: n_tokens = 402, truncated = 0 0.46.244.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 46129011 0.46.257.944 I slot launch_slot_: id 0 | task 2804 | processing task, is_child = 0 0.47.034.276 I slot print_timing: id 0 | task 2804 | prompt eval time = 101.29 ms / 345 tokens ( 0.29 ms per token, 3405.99 tokens per second) 0.47.034.282 I slot print_timing: id 0 | task 2804 | eval time = 675.02 ms / 53 tokens ( 12.98 ms per token, 77.03 tokens per second) 0.47.034.283 I slot print_timing: id 0 | task 2804 | total time = 776.32 ms / 398 tokens 0.47.034.284 I slot print_timing: id 0 | task 2804 | graphs reused = 2714 0.47.034.285 I slot print_timing: id 0 | task 2804 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.034.313 I slot release: id 0 | task 2804 | stop processing: n_tokens = 422, truncated = 0 0.47.062.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 46938480 0.47.077.486 I slot launch_slot_: id 0 | task 2858 | processing task, is_child = 0 0.47.814.725 I slot print_timing: id 0 | task 2858 | prompt eval time = 101.22 ms / 344 tokens ( 0.29 ms per token, 3398.47 tokens per second) 0.47.814.731 I slot print_timing: id 0 | task 2858 | eval time = 636.00 ms / 50 tokens ( 12.98 ms per token, 77.04 tokens per second) 0.47.814.732 I slot print_timing: id 0 | task 2858 | total time = 737.22 ms / 394 tokens 0.47.814.732 I slot print_timing: id 0 | task 2858 | graphs reused = 2762 0.47.814.733 I slot print_timing: id 0 | task 2858 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.814.761 I slot release: id 0 | task 2858 | stop processing: n_tokens = 418, truncated = 0 0.47.835.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 47718928 0.47.849.550 I slot launch_slot_: id 0 | task 2909 | processing task, is_child = 0 0.48.897.192 I slot print_timing: id 0 | task 2909 | prompt eval time = 101.68 ms / 378 tokens ( 0.27 ms per token, 3717.55 tokens per second) 0.48.897.198 I slot print_timing: id 0 | task 2909 | eval time = 945.95 ms / 74 tokens ( 12.96 ms per token, 77.17 tokens per second) 0.48.897.199 I slot print_timing: id 0 | task 2909 | total time = 1047.63 ms / 452 tokens 0.48.897.200 I slot print_timing: id 0 | task 2909 | graphs reused = 2834 0.48.897.201 I slot print_timing: id 0 | task 2909 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.897.229 I slot release: id 0 | task 2909 | stop processing: n_tokens = 476, truncated = 0 0.48.916.207 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 48801396 0.48.931.881 I slot launch_slot_: id 0 | task 2984 | processing task, is_child = 0 0.49.802.124 I slot print_timing: id 0 | task 2984 | prompt eval time = 91.89 ms / 331 tokens ( 0.28 ms per token, 3602.29 tokens per second) 0.49.802.131 I slot print_timing: id 0 | task 2984 | eval time = 778.34 ms / 61 tokens ( 12.97 ms per token, 77.09 tokens per second) 0.49.802.132 I slot print_timing: id 0 | task 2984 | total time = 870.23 ms / 392 tokens 0.49.802.134 I slot print_timing: id 0 | task 2984 | graphs reused = 2893 0.49.802.135 I slot print_timing: id 0 | task 2984 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.802.167 I slot release: id 0 | task 2984 | stop processing: n_tokens = 416, truncated = 0 0.49.828.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 49706334 0.49.842.599 I slot launch_slot_: id 0 | task 3046 | processing task, is_child = 0 0.50.589.421 I slot print_timing: id 0 | task 3046 | prompt eval time = 123.52 ms / 387 tokens ( 0.32 ms per token, 3133.07 tokens per second) 0.50.589.427 I slot print_timing: id 0 | task 3046 | eval time = 623.28 ms / 49 tokens ( 12.99 ms per token, 77.01 tokens per second) 0.50.589.428 I slot print_timing: id 0 | task 3046 | total time = 746.81 ms / 436 tokens 0.50.589.429 I slot print_timing: id 0 | task 3046 | graphs reused = 2940 0.50.589.430 I slot print_timing: id 0 | task 3046 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.589.461 I slot release: id 0 | task 3046 | stop processing: n_tokens = 460, truncated = 0 0.50.603.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 50493628 0.50.618.852 I slot launch_slot_: id 0 | task 3096 | processing task, is_child = 0 0.51.679.239 I slot print_timing: id 0 | task 3096 | prompt eval time = 101.37 ms / 345 tokens ( 0.29 ms per token, 3403.31 tokens per second) 0.51.679.245 I slot print_timing: id 0 | task 3096 | eval time = 959.00 ms / 75 tokens ( 12.96 ms per token, 77.16 tokens per second) 0.51.679.246 I slot print_timing: id 0 | task 3096 | total time = 1060.37 ms / 420 tokens 0.51.679.247 I slot print_timing: id 0 | task 3096 | graphs reused = 3013 0.51.679.248 I slot print_timing: id 0 | task 3096 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.679.278 I slot release: id 0 | task 3096 | stop processing: n_tokens = 444, truncated = 0 0.51.708.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 51583445 0.51.723.214 I slot launch_slot_: id 0 | task 3172 | processing task, is_child = 0 0.52.619.209 I slot print_timing: id 0 | task 3172 | prompt eval time = 100.94 ms / 337 tokens ( 0.30 ms per token, 3338.52 tokens per second) 0.52.619.215 I slot print_timing: id 0 | task 3172 | eval time = 795.04 ms / 61 tokens ( 13.25 ms per token, 75.47 tokens per second) 0.52.619.216 I slot print_timing: id 0 | task 3172 | total time = 895.98 ms / 398 tokens 0.52.619.217 I slot print_timing: id 0 | task 3172 | graphs reused = 3072 0.52.619.218 I slot print_timing: id 0 | task 3172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.619.246 I slot release: id 0 | task 3172 | stop processing: n_tokens = 422, truncated = 0 0.52.634.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 52523413 0.52.649.762 I slot launch_slot_: id 0 | task 3234 | processing task, is_child = 0 0.54.016.581 I slot print_timing: id 0 | task 3234 | prompt eval time = 138.58 ms / 463 tokens ( 0.30 ms per token, 3340.96 tokens per second) 0.54.016.587 I slot print_timing: id 0 | task 3234 | eval time = 1228.21 ms / 95 tokens ( 13.07 ms per token, 76.53 tokens per second) 0.54.016.588 I slot print_timing: id 0 | task 3234 | total time = 1366.80 ms / 558 tokens 0.54.016.589 I slot print_timing: id 0 | task 3234 | graphs reused = 3164 0.54.016.590 I slot print_timing: id 0 | task 3234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.016.622 I slot release: id 0 | task 3234 | stop processing: n_tokens = 582, truncated = 0 0.54.037.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 53920789 0.54.056.267 I slot launch_slot_: id 0 | task 3330 | processing task, is_child = 0 0.55.590.906 I slot print_timing: id 0 | task 3330 | prompt eval time = 125.66 ms / 440 tokens ( 0.29 ms per token, 3501.48 tokens per second) 0.55.590.912 I slot print_timing: id 0 | task 3330 | eval time = 1408.96 ms / 109 tokens ( 13.05 ms per token, 76.65 tokens per second) 0.55.590.913 I slot print_timing: id 0 | task 3330 | total time = 1534.62 ms / 549 tokens 0.55.590.914 I slot print_timing: id 0 | task 3330 | graphs reused = 3270 0.55.590.914 I slot print_timing: id 0 | task 3330 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.590.945 I slot release: id 0 | task 3330 | stop processing: n_tokens = 573, truncated = 0 0.55.595.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 55495112 0.55.617.466 I slot launch_slot_: id 0 | task 3440 | processing task, is_child = 0 0.56.527.590 I slot print_timing: id 0 | task 3440 | prompt eval time = 92.17 ms / 336 tokens ( 0.27 ms per token, 3645.28 tokens per second) 0.56.527.595 I slot print_timing: id 0 | task 3440 | eval time = 817.93 ms / 64 tokens ( 12.98 ms per token, 77.02 tokens per second) 0.56.527.596 I slot print_timing: id 0 | task 3440 | total time = 910.11 ms / 400 tokens 0.56.527.597 I slot print_timing: id 0 | task 3440 | graphs reused = 3332 0.56.527.598 I slot print_timing: id 0 | task 3440 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.527.626 I slot release: id 0 | task 3440 | stop processing: n_tokens = 424, truncated = 0 0.56.549.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 56431793 0.56.564.012 I slot launch_slot_: id 0 | task 3505 | processing task, is_child = 0 0.57.400.998 I slot print_timing: id 0 | task 3505 | prompt eval time = 102.12 ms / 367 tokens ( 0.28 ms per token, 3593.71 tokens per second) 0.57.401.004 I slot print_timing: id 0 | task 3505 | eval time = 734.85 ms / 57 tokens ( 13.12 ms per token, 76.21 tokens per second) 0.57.401.005 I slot print_timing: id 0 | task 3505 | total time = 836.97 ms / 424 tokens 0.57.401.006 I slot print_timing: id 0 | task 3505 | graphs reused = 3387 0.57.401.007 I slot print_timing: id 0 | task 3505 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.401.037 I slot release: id 0 | task 3505 | stop processing: n_tokens = 448, truncated = 0 0.57.405.255 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 57305204 0.57.420.691 I slot launch_slot_: id 0 | task 3563 | processing task, is_child = 0 0.58.175.589 I slot print_timing: id 0 | task 3563 | prompt eval time = 92.03 ms / 327 tokens ( 0.28 ms per token, 3553.19 tokens per second) 0.58.175.594 I slot print_timing: id 0 | task 3563 | eval time = 662.85 ms / 52 tokens ( 13.00 ms per token, 76.94 tokens per second) 0.58.175.595 I slot print_timing: id 0 | task 3563 | total time = 754.88 ms / 379 tokens 0.58.175.596 I slot print_timing: id 0 | task 3563 | graphs reused = 3437 0.58.175.597 I slot print_timing: id 0 | task 3563 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.175.625 I slot release: id 0 | task 3563 | stop processing: n_tokens = 403, truncated = 0 0.58.199.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 58079792 0.58.213.813 I slot launch_slot_: id 0 | task 3616 | processing task, is_child = 0 0.59.319.284 I slot print_timing: id 0 | task 3616 | prompt eval time = 123.55 ms / 393 tokens ( 0.31 ms per token, 3180.92 tokens per second) 0.59.319.290 I slot print_timing: id 0 | task 3616 | eval time = 981.91 ms / 76 tokens ( 13.09 ms per token, 76.38 tokens per second) 0.59.319.292 I slot print_timing: id 0 | task 3616 | total time = 1105.46 ms / 469 tokens 0.59.319.292 I slot print_timing: id 0 | task 3616 | graphs reused = 3511 0.59.319.293 I slot print_timing: id 0 | task 3616 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.319.326 I slot release: id 0 | task 3616 | stop processing: n_tokens = 493, truncated = 0 0.59.324.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 59223493 0.59.341.318 I slot launch_slot_: id 0 | task 3693 | processing task, is_child = 0 1.00.300.326 I slot print_timing: id 0 | task 3693 | prompt eval time = 161.73 ms / 524 tokens ( 0.31 ms per token, 3239.97 tokens per second) 1.00.300.331 I slot print_timing: id 0 | task 3693 | eval time = 797.26 ms / 62 tokens ( 13.07 ms per token, 76.51 tokens per second) 1.00.300.332 I slot print_timing: id 0 | task 3693 | total time = 958.99 ms / 586 tokens 1.00.300.334 I slot print_timing: id 0 | task 3693 | graphs reused = 3571 1.00.300.334 I slot print_timing: id 0 | task 3693 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.300.367 I slot release: id 0 | task 3693 | stop processing: n_tokens = 610, truncated = 0 1.00.326.477 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 60204534 1.00.347.172 I slot launch_slot_: id 0 | task 3756 | processing task, is_child = 0 1.01.310.944 I slot print_timing: id 0 | task 3756 | prompt eval time = 178.99 ms / 602 tokens ( 0.30 ms per token, 3363.26 tokens per second) 1.01.310.949 I slot print_timing: id 0 | task 3756 | eval time = 784.76 ms / 61 tokens ( 13.08 ms per token, 76.46 tokens per second) 1.01.310.950 I slot print_timing: id 0 | task 3756 | total time = 963.76 ms / 663 tokens 1.01.310.951 I slot print_timing: id 0 | task 3756 | graphs reused = 3630 1.01.310.952 I slot print_timing: id 0 | task 3756 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.310.988 I slot release: id 0 | task 3756 | stop processing: n_tokens = 687, truncated = 0 1.01.328.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 61215155 1.01.350.407 I slot launch_slot_: id 0 | task 3818 | processing task, is_child = 0 1.02.341.664 I slot print_timing: id 0 | task 3818 | prompt eval time = 181.24 ms / 640 tokens ( 0.28 ms per token, 3531.29 tokens per second) 1.02.341.670 I slot print_timing: id 0 | task 3818 | eval time = 810.00 ms / 63 tokens ( 13.06 ms per token, 76.54 tokens per second) 1.02.341.671 I slot print_timing: id 0 | task 3818 | total time = 991.24 ms / 703 tokens 1.02.341.672 I slot print_timing: id 0 | task 3818 | graphs reused = 3691 1.02.341.673 I slot print_timing: id 0 | task 3818 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.341.709 I slot release: id 0 | task 3818 | stop processing: n_tokens = 727, truncated = 0 1.02.368.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 62245876 1.02.391.769 I slot launch_slot_: id 0 | task 3882 | processing task, is_child = 0 1.03.369.896 I slot print_timing: id 0 | task 3882 | prompt eval time = 181.02 ms / 629 tokens ( 0.29 ms per token, 3474.77 tokens per second) 1.03.369.901 I slot print_timing: id 0 | task 3882 | eval time = 797.09 ms / 62 tokens ( 13.07 ms per token, 76.53 tokens per second) 1.03.369.902 I slot print_timing: id 0 | task 3882 | total time = 978.11 ms / 691 tokens 1.03.369.903 I slot print_timing: id 0 | task 3882 | graphs reused = 3751 1.03.369.904 I slot print_timing: id 0 | task 3882 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.369.939 I slot release: id 0 | task 3882 | stop processing: n_tokens = 715, truncated = 0 1.03.394.231 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 63274106 1.03.417.084 I slot launch_slot_: id 0 | task 3945 | processing task, is_child = 0 1.04.289.330 I slot print_timing: id 0 | task 3945 | prompt eval time = 138.36 ms / 458 tokens ( 0.30 ms per token, 3310.23 tokens per second) 1.04.289.335 I slot print_timing: id 0 | task 3945 | eval time = 733.87 ms / 57 tokens ( 13.10 ms per token, 76.31 tokens per second) 1.04.289.337 I slot print_timing: id 0 | task 3945 | total time = 872.23 ms / 515 tokens 1.04.289.337 I slot print_timing: id 0 | task 3945 | graphs reused = 3805 1.04.289.338 I slot print_timing: id 0 | task 3945 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.289.369 I slot release: id 0 | task 3945 | stop processing: n_tokens = 539, truncated = 0 1.04.318.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 64193536 1.04.336.366 I slot launch_slot_: id 0 | task 4003 | processing task, is_child = 0 1.05.320.859 I slot print_timing: id 0 | task 4003 | prompt eval time = 173.63 ms / 594 tokens ( 0.29 ms per token, 3421.13 tokens per second) 1.05.320.865 I slot print_timing: id 0 | task 4003 | eval time = 810.85 ms / 63 tokens ( 13.08 ms per token, 76.46 tokens per second) 1.05.320.866 I slot print_timing: id 0 | task 4003 | total time = 984.48 ms / 657 tokens 1.05.320.867 I slot print_timing: id 0 | task 4003 | graphs reused = 3866 1.05.320.868 I slot print_timing: id 0 | task 4003 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.320.905 I slot release: id 0 | task 4003 | stop processing: n_tokens = 681, truncated = 0 1.05.326.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 65225072 1.05.348.031 I slot launch_slot_: id 0 | task 4067 | processing task, is_child = 0 1.06.169.624 I slot print_timing: id 0 | task 4067 | prompt eval time = 166.75 ms / 572 tokens ( 0.29 ms per token, 3430.26 tokens per second) 1.06.169.630 I slot print_timing: id 0 | task 4067 | eval time = 654.83 ms / 51 tokens ( 13.10 ms per token, 76.36 tokens per second) 1.06.169.631 I slot print_timing: id 0 | task 4067 | total time = 821.58 ms / 623 tokens 1.06.169.632 I slot print_timing: id 0 | task 4067 | graphs reused = 3915 1.06.169.633 I slot print_timing: id 0 | task 4067 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.169.668 I slot release: id 0 | task 4067 | stop processing: n_tokens = 647, truncated = 0 1.06.192.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 66073835 1.06.213.710 I slot launch_slot_: id 0 | task 4119 | processing task, is_child = 0 1.06.996.388 I slot print_timing: id 0 | task 4119 | prompt eval time = 141.18 ms / 502 tokens ( 0.28 ms per token, 3555.85 tokens per second) 1.06.996.394 I slot print_timing: id 0 | task 4119 | eval time = 641.48 ms / 50 tokens ( 13.09 ms per token, 76.39 tokens per second) 1.06.996.396 I slot print_timing: id 0 | task 4119 | total time = 782.66 ms / 552 tokens 1.06.996.397 I slot print_timing: id 0 | task 4119 | graphs reused = 3963 1.06.996.398 I slot print_timing: id 0 | task 4119 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.996.439 I slot release: id 0 | task 4119 | stop processing: n_tokens = 576, truncated = 0 1.07.024.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 66900606 1.07.043.794 I slot launch_slot_: id 0 | task 4170 | processing task, is_child = 0 1.07.918.630 I slot print_timing: id 0 | task 4170 | prompt eval time = 138.64 ms / 479 tokens ( 0.29 ms per token, 3454.89 tokens per second) 1.07.918.636 I slot print_timing: id 0 | task 4170 | eval time = 736.17 ms / 57 tokens ( 13.15 ms per token, 76.07 tokens per second) 1.07.918.637 I slot print_timing: id 0 | task 4170 | total time = 874.82 ms / 536 tokens 1.07.918.638 I slot print_timing: id 0 | task 4170 | graphs reused = 4017 1.07.918.639 I slot print_timing: id 0 | task 4170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.918.671 I slot release: id 0 | task 4170 | stop processing: n_tokens = 560, truncated = 0 1.07.938.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 67822838 1.07.958.026 I slot launch_slot_: id 0 | task 4228 | processing task, is_child = 0 1.08.695.765 I slot print_timing: id 0 | task 4228 | prompt eval time = 161.92 ms / 552 tokens ( 0.29 ms per token, 3409.13 tokens per second) 1.08.695.771 I slot print_timing: id 0 | task 4228 | eval time = 575.80 ms / 45 tokens ( 13.09 ms per token, 76.42 tokens per second) 1.08.695.772 I slot print_timing: id 0 | task 4228 | total time = 737.72 ms / 597 tokens 1.08.695.773 I slot print_timing: id 0 | task 4228 | graphs reused = 4060 1.08.695.774 I slot print_timing: id 0 | task 4228 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.695.807 I slot release: id 0 | task 4228 | stop processing: n_tokens = 621, truncated = 0 1.08.716.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 68599973 1.08.737.103 I slot launch_slot_: id 0 | task 4274 | processing task, is_child = 0 1.10.363.900 I slot print_timing: id 0 | task 4274 | prompt eval time = 153.70 ms / 514 tokens ( 0.30 ms per token, 3344.26 tokens per second) 1.10.363.906 I slot print_timing: id 0 | task 4274 | eval time = 1473.09 ms / 114 tokens ( 13.04 ms per token, 76.71 tokens per second) 1.10.363.907 I slot print_timing: id 0 | task 4274 | total time = 1626.78 ms / 628 tokens 1.10.363.908 I slot print_timing: id 0 | task 4274 | graphs reused = 4172 1.10.363.909 I slot print_timing: id 0 | task 4274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.363.941 I slot release: id 0 | task 4274 | stop processing: n_tokens = 652, truncated = 0 1.10.388.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 652, t_last = 70268108 1.10.409.485 I slot launch_slot_: id 0 | task 4389 | processing task, is_child = 0 1.11.068.412 I slot print_timing: id 0 | task 4389 | prompt eval time = 125.23 ms / 428 tokens ( 0.29 ms per token, 3417.74 tokens per second) 1.11.068.418 I slot print_timing: id 0 | task 4389 | eval time = 533.68 ms / 42 tokens ( 13.02 ms per token, 76.82 tokens per second) 1.11.068.420 I slot print_timing: id 0 | task 4389 | total time = 658.91 ms / 470 tokens 1.11.068.421 I slot print_timing: id 0 | task 4389 | graphs reused = 4212 1.11.068.422 I slot print_timing: id 0 | task 4389 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.068.457 I slot release: id 0 | task 4389 | stop processing: n_tokens = 494, truncated = 0 1.11.094.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 70972624 1.11.110.820 I slot launch_slot_: id 0 | task 4432 | processing task, is_child = 0 1.12.127.118 I slot print_timing: id 0 | task 4432 | prompt eval time = 158.31 ms / 521 tokens ( 0.30 ms per token, 3290.97 tokens per second) 1.12.127.124 I slot print_timing: id 0 | task 4432 | eval time = 857.97 ms / 66 tokens ( 13.20 ms per token, 75.76 tokens per second) 1.12.127.125 I slot print_timing: id 0 | task 4432 | total time = 1016.28 ms / 587 tokens 1.12.127.126 I slot print_timing: id 0 | task 4432 | graphs reused = 4276 1.12.127.127 I slot print_timing: id 0 | task 4432 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.127.159 I slot release: id 0 | task 4432 | stop processing: n_tokens = 611, truncated = 0 1.12.153.532 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 72031326 1.12.173.324 I slot launch_slot_: id 0 | task 4499 | processing task, is_child = 0 1.12.977.536 I slot print_timing: id 0 | task 4499 | prompt eval time = 138.37 ms / 472 tokens ( 0.29 ms per token, 3411.09 tokens per second) 1.12.977.541 I slot print_timing: id 0 | task 4499 | eval time = 665.82 ms / 51 tokens ( 13.32 ms per token, 75.10 tokens per second) 1.12.977.542 I slot print_timing: id 0 | task 4499 | total time = 804.19 ms / 523 tokens 1.12.977.543 I slot print_timing: id 0 | task 4499 | graphs reused = 4324 1.12.977.544 I slot print_timing: id 0 | task 4499 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.977.579 I slot release: id 0 | task 4499 | stop processing: n_tokens = 547, truncated = 0 1.12.993.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 72881746 1.13.012.541 I slot launch_slot_: id 0 | task 4551 | processing task, is_child = 0 1.13.698.444 I slot print_timing: id 0 | task 4551 | prompt eval time = 125.20 ms / 428 tokens ( 0.29 ms per token, 3418.61 tokens per second) 1.13.698.450 I slot print_timing: id 0 | task 4551 | eval time = 560.69 ms / 44 tokens ( 13.04 ms per token, 76.69 tokens per second) 1.13.698.451 I slot print_timing: id 0 | task 4551 | total time = 685.88 ms / 472 tokens 1.13.698.452 I slot print_timing: id 0 | task 4551 | graphs reused = 4366 1.13.698.453 I slot print_timing: id 0 | task 4551 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.698.485 I slot release: id 0 | task 4551 | stop processing: n_tokens = 496, truncated = 0 1.13.722.252 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 73602652 1.13.738.775 I slot launch_slot_: id 0 | task 4596 | processing task, is_child = 0 1.14.457.186 I slot print_timing: id 0 | task 4596 | prompt eval time = 138.55 ms / 456 tokens ( 0.30 ms per token, 3291.30 tokens per second) 1.14.457.192 I slot print_timing: id 0 | task 4596 | eval time = 579.85 ms / 45 tokens ( 13.18 ms per token, 75.88 tokens per second) 1.14.457.193 I slot print_timing: id 0 | task 4596 | total time = 718.40 ms / 501 tokens 1.14.457.194 I slot print_timing: id 0 | task 4596 | graphs reused = 4408 1.14.457.196 I slot print_timing: id 0 | task 4596 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.457.228 I slot release: id 0 | task 4596 | stop processing: n_tokens = 525, truncated = 0 1.14.462.151 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 74361395 1.14.479.603 I slot launch_slot_: id 0 | task 4642 | processing task, is_child = 0 1.15.165.612 I slot print_timing: id 0 | task 4642 | prompt eval time = 125.83 ms / 439 tokens ( 0.29 ms per token, 3488.70 tokens per second) 1.15.165.618 I slot print_timing: id 0 | task 4642 | eval time = 560.16 ms / 44 tokens ( 13.03 ms per token, 76.76 tokens per second) 1.15.165.619 I slot print_timing: id 0 | task 4642 | total time = 686.00 ms / 483 tokens 1.15.165.620 I slot print_timing: id 0 | task 4642 | graphs reused = 4450 1.15.165.621 I slot print_timing: id 0 | task 4642 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.165.656 I slot release: id 0 | task 4642 | stop processing: n_tokens = 507, truncated = 0 1.15.171.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 75069823 1.15.188.829 I slot launch_slot_: id 0 | task 4687 | processing task, is_child = 0 1.16.135.350 I slot print_timing: id 0 | task 4687 | prompt eval time = 174.24 ms / 600 tokens ( 0.29 ms per token, 3443.47 tokens per second) 1.16.135.355 I slot print_timing: id 0 | task 4687 | eval time = 772.26 ms / 60 tokens ( 13.09 ms per token, 76.40 tokens per second) 1.16.135.356 I slot print_timing: id 0 | task 4687 | total time = 946.50 ms / 660 tokens 1.16.135.357 I slot print_timing: id 0 | task 4687 | graphs reused = 4508 1.16.135.358 I slot print_timing: id 0 | task 4687 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.135.396 I slot release: id 0 | task 4687 | stop processing: n_tokens = 684, truncated = 0 1.16.140.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 76039563 1.16.162.294 I slot launch_slot_: id 0 | task 4748 | processing task, is_child = 0 1.16.842.437 I slot print_timing: id 0 | task 4748 | prompt eval time = 138.62 ms / 473 tokens ( 0.29 ms per token, 3412.21 tokens per second) 1.16.842.443 I slot print_timing: id 0 | task 4748 | eval time = 541.51 ms / 42 tokens ( 13.21 ms per token, 75.71 tokens per second) 1.16.842.445 I slot print_timing: id 0 | task 4748 | total time = 680.13 ms / 515 tokens 1.16.842.445 I slot print_timing: id 0 | task 4748 | graphs reused = 4547 1.16.842.446 I slot print_timing: id 0 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.842.479 I slot release: id 0 | task 4748 | stop processing: n_tokens = 539, truncated = 0 1.16.864.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 76746646 1.16.882.588 I slot launch_slot_: id 0 | task 4791 | processing task, is_child = 0 1.17.953.778 I slot print_timing: id 0 | task 4791 | prompt eval time = 231.87 ms / 835 tokens ( 0.28 ms per token, 3601.11 tokens per second) 1.17.953.783 I slot print_timing: id 0 | task 4791 | eval time = 839.30 ms / 65 tokens ( 13.11 ms per token, 76.25 tokens per second) 1.17.953.784 I slot print_timing: id 0 | task 4791 | total time = 1071.17 ms / 900 tokens 1.17.953.785 I slot print_timing: id 0 | task 4791 | graphs reused = 4610 1.17.953.786 I slot print_timing: id 0 | task 4791 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.953.829 I slot release: id 0 | task 4791 | stop processing: n_tokens = 924, truncated = 0 1.17.970.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 77857996 1.17.999.803 I slot launch_slot_: id 0 | task 4857 | processing task, is_child = 0 1.18.690.213 I slot print_timing: id 0 | task 4857 | prompt eval time = 138.37 ms / 454 tokens ( 0.30 ms per token, 3281.15 tokens per second) 1.18.690.219 I slot print_timing: id 0 | task 4857 | eval time = 552.03 ms / 43 tokens ( 13.14 ms per token, 76.08 tokens per second) 1.18.690.220 I slot print_timing: id 0 | task 4857 | total time = 690.39 ms / 497 tokens 1.18.690.221 I slot print_timing: id 0 | task 4857 | graphs reused = 4650 1.18.690.222 I slot print_timing: id 0 | task 4857 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.690.256 I slot release: id 0 | task 4857 | stop processing: n_tokens = 521, truncated = 0 1.18.696.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 78594423 1.18.713.856 I slot launch_slot_: id 0 | task 4901 | processing task, is_child = 0 1.19.522.745 I slot print_timing: id 0 | task 4901 | prompt eval time = 192.59 ms / 667 tokens ( 0.29 ms per token, 3463.23 tokens per second) 1.19.522.751 I slot print_timing: id 0 | task 4901 | eval time = 616.28 ms / 48 tokens ( 13.11 ms per token, 76.26 tokens per second) 1.19.522.752 I slot print_timing: id 0 | task 4901 | total time = 808.87 ms / 715 tokens 1.19.522.752 I slot print_timing: id 0 | task 4901 | graphs reused = 4696 1.19.522.753 I slot print_timing: id 0 | task 4901 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.522.793 I slot release: id 0 | task 4901 | stop processing: n_tokens = 741, truncated = 0 1.19.547.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 79426960 1.19.583.358 I slot launch_slot_: id 0 | task 4950 | processing task, is_child = 0 1.20.696.429 I slot print_timing: id 0 | task 4950 | prompt eval time = 181.87 ms / 628 tokens ( 0.29 ms per token, 3452.96 tokens per second) 1.20.696.435 I slot print_timing: id 0 | task 4950 | eval time = 931.18 ms / 69 tokens ( 13.69 ms per token, 73.03 tokens per second) 1.20.696.436 I slot print_timing: id 0 | task 4950 | total time = 1113.05 ms / 697 tokens 1.20.696.437 I slot print_timing: id 0 | task 4950 | graphs reused = 4763 1.20.696.438 I slot print_timing: id 0 | task 4950 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.696.479 I slot release: id 0 | task 4950 | stop processing: n_tokens = 858, truncated = 0 1.20.716.787 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 80600646 1.20.743.805 I slot launch_slot_: id 0 | task 5020 | processing task, is_child = 0 1.21.895.895 I slot print_timing: id 0 | task 5020 | prompt eval time = 171.12 ms / 578 tokens ( 0.30 ms per token, 3377.71 tokens per second) 1.21.895.901 I slot print_timing: id 0 | task 5020 | eval time = 980.95 ms / 76 tokens ( 13.08 ms per token, 76.46 tokens per second) 1.21.895.902 I slot print_timing: id 0 | task 5020 | total time = 1152.07 ms / 654 tokens 1.21.895.904 I slot print_timing: id 0 | task 5020 | graphs reused = 4837 1.21.895.905 I slot print_timing: id 0 | task 5020 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.895.943 I slot release: id 0 | task 5020 | stop processing: n_tokens = 678, truncated = 0 1.21.918.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 81800110 1.21.940.114 I slot launch_slot_: id 0 | task 5097 | processing task, is_child = 0 1.22.937.883 I slot print_timing: id 0 | task 5097 | prompt eval time = 139.65 ms / 461 tokens ( 0.30 ms per token, 3301.16 tokens per second) 1.22.937.888 I slot print_timing: id 0 | task 5097 | eval time = 858.10 ms / 66 tokens ( 13.20 ms per token, 75.75 tokens per second) 1.22.937.889 I slot print_timing: id 0 | task 5097 | total time = 997.75 ms / 527 tokens 1.22.937.890 I slot print_timing: id 0 | task 5097 | graphs reused = 4900 1.22.937.891 I slot print_timing: id 0 | task 5097 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.937.924 I slot release: id 0 | task 5097 | stop processing: n_tokens = 551, truncated = 0 1.22.966.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 82842090 1.22.984.584 I slot launch_slot_: id 0 | task 5164 | processing task, is_child = 0 1.23.946.228 I slot print_timing: id 0 | task 5164 | prompt eval time = 177.79 ms / 613 tokens ( 0.29 ms per token, 3447.79 tokens per second) 1.23.946.234 I slot print_timing: id 0 | task 5164 | eval time = 783.83 ms / 61 tokens ( 13.06 ms per token, 76.55 tokens per second) 1.23.946.235 I slot print_timing: id 0 | task 5164 | total time = 961.63 ms / 674 tokens 1.23.946.236 I slot print_timing: id 0 | task 5164 | graphs reused = 4959 1.23.946.237 I slot print_timing: id 0 | task 5164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.946.275 I slot release: id 0 | task 5164 | stop processing: n_tokens = 698, truncated = 0 1.23.962.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 698, t_last = 83850442 1.23.984.378 I slot launch_slot_: id 0 | task 5226 | processing task, is_child = 0 1.25.044.360 I slot print_timing: id 0 | task 5226 | prompt eval time = 222.23 ms / 794 tokens ( 0.28 ms per token, 3572.84 tokens per second) 1.25.044.366 I slot print_timing: id 0 | task 5226 | eval time = 837.74 ms / 65 tokens ( 13.09 ms per token, 76.40 tokens per second) 1.25.044.367 I slot print_timing: id 0 | task 5226 | total time = 1059.97 ms / 859 tokens 1.25.044.368 I slot print_timing: id 0 | task 5226 | graphs reused = 5022 1.25.044.369 I slot print_timing: id 0 | task 5226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.044.412 I slot release: id 0 | task 5226 | stop processing: n_tokens = 883, truncated = 0 1.25.064.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 84948579 1.25.110.780 I slot launch_slot_: id 0 | task 5292 | processing task, is_child = 0 1.25.982.293 I slot print_timing: id 0 | task 5292 | prompt eval time = 126.31 ms / 431 tokens ( 0.29 ms per token, 3412.29 tokens per second) 1.25.982.299 I slot print_timing: id 0 | task 5292 | eval time = 745.18 ms / 58 tokens ( 13.07 ms per token, 76.49 tokens per second) 1.25.982.300 I slot print_timing: id 0 | task 5292 | total time = 871.49 ms / 489 tokens 1.25.982.301 I slot print_timing: id 0 | task 5292 | graphs reused = 5078 1.25.982.302 I slot print_timing: id 0 | task 5292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.982.340 I slot release: id 0 | task 5292 | stop processing: n_tokens = 687, truncated = 0 1.26.007.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 85886507 1.26.029.513 I slot launch_slot_: id 0 | task 5351 | processing task, is_child = 0 1.26.845.216 I slot print_timing: id 0 | task 5351 | prompt eval time = 165.81 ms / 563 tokens ( 0.29 ms per token, 3395.51 tokens per second) 1.26.845.222 I slot print_timing: id 0 | task 5351 | eval time = 649.88 ms / 50 tokens ( 13.26 ms per token, 75.40 tokens per second) 1.26.845.223 I slot print_timing: id 0 | task 5351 | total time = 815.69 ms / 613 tokens 1.26.845.224 I slot print_timing: id 0 | task 5351 | graphs reused = 5126 1.26.845.224 I slot print_timing: id 0 | task 5351 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.845.260 I slot release: id 0 | task 5351 | stop processing: n_tokens = 637, truncated = 0 1.26.863.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 86749427 1.26.896.268 I slot launch_slot_: id 0 | task 5402 | processing task, is_child = 0 1.27.601.821 I slot print_timing: id 0 | task 5402 | prompt eval time = 92.17 ms / 331 tokens ( 0.28 ms per token, 3591.39 tokens per second) 1.27.601.828 I slot print_timing: id 0 | task 5402 | eval time = 613.37 ms / 48 tokens ( 13.05 ms per token, 76.63 tokens per second) 1.27.601.830 I slot print_timing: id 0 | task 5402 | total time = 705.53 ms / 379 tokens 1.27.601.831 I slot print_timing: id 0 | task 5402 | graphs reused = 5171 1.27.601.832 I slot print_timing: id 0 | task 5402 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.601.866 I slot release: id 0 | task 5402 | stop processing: n_tokens = 513, truncated = 0 1.27.619.572 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 87506033 1.27.637.061 I slot launch_slot_: id 0 | task 5451 | processing task, is_child = 0 1.28.640.142 I slot print_timing: id 0 | task 5451 | prompt eval time = 141.34 ms / 489 tokens ( 0.29 ms per token, 3459.67 tokens per second) 1.28.640.148 I slot print_timing: id 0 | task 5451 | eval time = 861.72 ms / 67 tokens ( 13.06 ms per token, 76.59 tokens per second) 1.28.640.149 I slot print_timing: id 0 | task 5451 | total time = 1003.06 ms / 556 tokens 1.28.640.150 I slot print_timing: id 0 | task 5451 | graphs reused = 5236 1.28.640.151 I slot print_timing: id 0 | task 5451 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.640.183 I slot release: id 0 | task 5451 | stop processing: n_tokens = 580, truncated = 0 1.28.665.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 88544350 1.28.684.745 I slot launch_slot_: id 0 | task 5519 | processing task, is_child = 0 1.29.519.981 I slot print_timing: id 0 | task 5519 | prompt eval time = 141.48 ms / 510 tokens ( 0.28 ms per token, 3604.78 tokens per second) 1.29.519.988 I slot print_timing: id 0 | task 5519 | eval time = 693.74 ms / 54 tokens ( 13.09 ms per token, 76.40 tokens per second) 1.29.519.989 I slot print_timing: id 0 | task 5519 | total time = 835.22 ms / 564 tokens 1.29.519.990 I slot print_timing: id 0 | task 5519 | graphs reused = 5288 1.29.519.990 I slot print_timing: id 0 | task 5519 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.520.028 I slot release: id 0 | task 5519 | stop processing: n_tokens = 588, truncated = 0 1.29.540.208 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 89424195 1.29.559.481 I slot launch_slot_: id 0 | task 5574 | processing task, is_child = 0 1.30.655.606 I slot print_timing: id 0 | task 5574 | prompt eval time = 181.31 ms / 631 tokens ( 0.29 ms per token, 3480.21 tokens per second) 1.30.655.611 I slot print_timing: id 0 | task 5574 | eval time = 914.80 ms / 71 tokens ( 13.07 ms per token, 76.52 tokens per second) 1.30.655.612 I slot print_timing: id 0 | task 5574 | total time = 1096.11 ms / 702 tokens 1.30.655.614 I slot print_timing: id 0 | task 5574 | graphs reused = 5357 1.30.655.614 I slot print_timing: id 0 | task 5574 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.655.653 I slot release: id 0 | task 5574 | stop processing: n_tokens = 726, truncated = 0 1.30.684.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 90559819 1.30.713.804 I slot launch_slot_: id 0 | task 5646 | processing task, is_child = 0 1.31.573.965 I slot print_timing: id 0 | task 5646 | prompt eval time = 166.29 ms / 570 tokens ( 0.29 ms per token, 3427.68 tokens per second) 1.31.573.970 I slot print_timing: id 0 | task 5646 | eval time = 693.85 ms / 54 tokens ( 13.09 ms per token, 76.39 tokens per second) 1.31.573.971 I slot print_timing: id 0 | task 5646 | total time = 860.14 ms / 624 tokens 1.31.573.973 I slot print_timing: id 0 | task 5646 | graphs reused = 5409 1.31.573.974 I slot print_timing: id 0 | task 5646 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.574.009 I slot release: id 0 | task 5646 | stop processing: n_tokens = 648, truncated = 0 1.31.604.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 91478176 1.31.625.629 I slot launch_slot_: id 0 | task 5701 | processing task, is_child = 0 1.32.478.308 I slot print_timing: id 0 | task 5701 | prompt eval time = 221.88 ms / 792 tokens ( 0.28 ms per token, 3569.43 tokens per second) 1.32.478.314 I slot print_timing: id 0 | task 5701 | eval time = 630.78 ms / 49 tokens ( 13.14 ms per token, 76.10 tokens per second) 1.32.478.315 I slot print_timing: id 0 | task 5701 | total time = 852.66 ms / 841 tokens 1.32.478.316 I slot print_timing: id 0 | task 5701 | graphs reused = 5456 1.32.478.317 I slot print_timing: id 0 | task 5701 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.478.359 I slot release: id 0 | task 5701 | stop processing: n_tokens = 867, truncated = 0 1.32.498.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 92382526 1.32.526.068 I slot launch_slot_: id 0 | task 5751 | processing task, is_child = 0 1.33.268.298 I slot print_timing: id 0 | task 5751 | prompt eval time = 165.79 ms / 564 tokens ( 0.29 ms per token, 3401.87 tokens per second) 1.33.268.303 I slot print_timing: id 0 | task 5751 | eval time = 576.42 ms / 45 tokens ( 13.10 ms per token, 76.33 tokens per second) 1.33.268.305 I slot print_timing: id 0 | task 5751 | total time = 742.21 ms / 609 tokens 1.33.268.306 I slot print_timing: id 0 | task 5751 | graphs reused = 5499 1.33.268.307 I slot print_timing: id 0 | task 5751 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.268.343 I slot release: id 0 | task 5751 | stop processing: n_tokens = 635, truncated = 0 1.33.292.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 93172510 1.33.313.304 I slot launch_slot_: id 0 | task 5797 | processing task, is_child = 0 1.34.196.543 I slot print_timing: id 0 | task 5797 | prompt eval time = 177.16 ms / 617 tokens ( 0.29 ms per token, 3482.65 tokens per second) 1.34.196.549 I slot print_timing: id 0 | task 5797 | eval time = 706.06 ms / 55 tokens ( 13.08 ms per token, 76.48 tokens per second) 1.34.196.550 I slot print_timing: id 0 | task 5797 | total time = 883.22 ms / 672 tokens 1.34.196.551 I slot print_timing: id 0 | task 5797 | graphs reused = 5552 1.34.196.552 I slot print_timing: id 0 | task 5797 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.196.589 I slot release: id 0 | task 5797 | stop processing: n_tokens = 696, truncated = 0 1.34.213.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 696, t_last = 94100756 1.34.235.520 I slot launch_slot_: id 0 | task 5853 | processing task, is_child = 0 1.35.264.123 I slot print_timing: id 0 | task 5853 | prompt eval time = 166.25 ms / 572 tokens ( 0.29 ms per token, 3440.70 tokens per second) 1.35.264.129 I slot print_timing: id 0 | task 5853 | eval time = 862.34 ms / 67 tokens ( 13.07 ms per token, 76.54 tokens per second) 1.35.264.130 I slot print_timing: id 0 | task 5853 | total time = 1028.59 ms / 639 tokens 1.35.264.131 I slot print_timing: id 0 | task 5853 | graphs reused = 5617 1.35.264.132 I slot print_timing: id 0 | task 5853 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.264.167 I slot release: id 0 | task 5853 | stop processing: n_tokens = 663, truncated = 0 1.35.285.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 95168334 1.35.306.501 I slot launch_slot_: id 0 | task 5921 | processing task, is_child = 0 1.36.210.857 I slot print_timing: id 0 | task 5921 | prompt eval time = 204.75 ms / 712 tokens ( 0.29 ms per token, 3477.38 tokens per second) 1.36.210.863 I slot print_timing: id 0 | task 5921 | eval time = 699.59 ms / 54 tokens ( 13.20 ms per token, 75.76 tokens per second) 1.36.210.864 I slot print_timing: id 0 | task 5921 | total time = 904.34 ms / 766 tokens 1.36.210.865 I slot print_timing: id 0 | task 5921 | graphs reused = 5668 1.36.210.866 I slot print_timing: id 0 | task 5921 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.210.910 I slot release: id 0 | task 5921 | stop processing: n_tokens = 790, truncated = 0 1.36.241.398 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 96115077 1.36.266.849 I slot launch_slot_: id 0 | task 5976 | processing task, is_child = 0 1.37.883.901 I slot print_timing: id 0 | task 5976 | prompt eval time = 221.91 ms / 791 tokens ( 0.28 ms per token, 3564.46 tokens per second) 1.37.883.908 I slot print_timing: id 0 | task 5976 | eval time = 1395.12 ms / 106 tokens ( 13.29 ms per token, 75.26 tokens per second) 1.37.883.909 I slot print_timing: id 0 | task 5976 | total time = 1617.04 ms / 897 tokens 1.37.883.911 I slot print_timing: id 0 | task 5976 | graphs reused = 5772 1.37.883.912 I slot print_timing: id 0 | task 5976 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.883.958 I slot release: id 0 | task 5976 | stop processing: n_tokens = 921, truncated = 0 1.37.902.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 97788125 1.37.931.274 I slot launch_slot_: id 0 | task 6083 | processing task, is_child = 0 1.41.035.544 I slot print_timing: id 0 | task 6083 | n_gen = 232, tg = 76.92 t/s, tg_3s = 77.26 t/s 1.44.043.299 I slot print_timing: id 0 | task 6083 | n_gen = 463, tg = 76.86 t/s, tg_3s = 76.80 t/s 1.47.053.498 I slot print_timing: id 0 | task 6083 | n_gen = 693, tg = 76.71 t/s, tg_3s = 76.41 t/s 1.50.056.524 I slot print_timing: id 0 | task 6083 | n_gen = 916, tg = 76.10 t/s, tg_3s = 74.26 t/s 1.51.528.423 I slot print_timing: id 0 | task 6083 | prompt eval time = 101.25 ms / 369 tokens ( 0.27 ms per token, 3644.41 tokens per second) 1.51.528.429 I slot print_timing: id 0 | task 6083 | eval time = 13495.88 ms / 1024 tokens ( 13.19 ms per token, 75.80 tokens per second) 1.51.528.430 I slot print_timing: id 0 | task 6083 | total time = 13597.13 ms / 1393 tokens 1.51.528.430 I slot print_timing: id 0 | task 6083 | graphs reused = 6790 1.51.528.431 I slot print_timing: id 0 | task 6083 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.528.460 I slot release: id 0 | task 6083 | stop processing: n_tokens = 1417, truncated = 0 1.51.547.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1417, t_last = 111432627 1.51.547.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.51.597.202 I slot launch_slot_: id 0 | task 7108 | processing task, is_child = 0 1.52.516.692 I slot print_timing: id 0 | task 7108 | prompt eval time = 123.68 ms / 388 tokens ( 0.32 ms per token, 3137.08 tokens per second) 1.52.516.698 I slot print_timing: id 0 | task 7108 | eval time = 795.79 ms / 62 tokens ( 13.05 ms per token, 76.65 tokens per second) 1.52.516.699 I slot print_timing: id 0 | task 7108 | total time = 919.47 ms / 450 tokens 1.52.516.700 I slot print_timing: id 0 | task 7108 | graphs reused = 6850 1.52.516.701 I slot print_timing: id 0 | task 7108 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.516.734 I slot release: id 0 | task 7108 | stop processing: n_tokens = 474, truncated = 0 1.52.530.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 112420901 1.52.530.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.52.551.614 I slot launch_slot_: id 0 | task 7171 | processing task, is_child = 0 1.53.514.373 I slot print_timing: id 0 | task 7171 | prompt eval time = 102.07 ms / 370 tokens ( 0.28 ms per token, 3624.89 tokens per second) 1.53.514.378 I slot print_timing: id 0 | task 7171 | eval time = 860.67 ms / 66 tokens ( 13.24 ms per token, 75.52 tokens per second) 1.53.514.380 I slot print_timing: id 0 | task 7171 | total time = 962.74 ms / 436 tokens 1.53.514.381 I slot print_timing: id 0 | task 7171 | graphs reused = 6914 1.53.514.382 I slot print_timing: id 0 | task 7171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.514.412 I slot release: id 0 | task 7171 | stop processing: n_tokens = 460, truncated = 0 1.53.531.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 113418579 1.53.531.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.53.551.013 I slot launch_slot_: id 0 | task 7238 | processing task, is_child = 0 1.54.422.414 I slot print_timing: id 0 | task 7238 | prompt eval time = 101.08 ms / 340 tokens ( 0.30 ms per token, 3363.61 tokens per second) 1.54.422.420 I slot print_timing: id 0 | task 7238 | eval time = 770.30 ms / 60 tokens ( 13.06 ms per token, 76.59 tokens per second) 1.54.422.421 I slot print_timing: id 0 | task 7238 | total time = 871.39 ms / 400 tokens 1.54.422.422 I slot print_timing: id 0 | task 7238 | graphs reused = 6972 1.54.422.422 I slot print_timing: id 0 | task 7238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.422.451 I slot release: id 0 | task 7238 | stop processing: n_tokens = 424, truncated = 0 1.54.426.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 114326618 1.54.426.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.54.445.535 I slot launch_slot_: id 0 | task 7299 | processing task, is_child = 0 1.55.572.826 I slot print_timing: id 0 | task 7299 | prompt eval time = 124.68 ms / 409 tokens ( 0.30 ms per token, 3280.29 tokens per second) 1.55.572.832 I slot print_timing: id 0 | task 7299 | eval time = 1002.59 ms / 78 tokens ( 13.02 ms per token, 76.80 tokens per second) 1.55.572.833 I slot print_timing: id 0 | task 7299 | total time = 1127.28 ms / 487 tokens 1.55.572.834 I slot print_timing: id 0 | task 7299 | graphs reused = 7048 1.55.572.834 I slot print_timing: id 0 | task 7299 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.572.865 I slot release: id 0 | task 7299 | stop processing: n_tokens = 511, truncated = 0 1.55.593.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 115477032 1.55.593.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 1.55.597.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.55.619.189 I slot launch_slot_: id 0 | task 7378 | processing task, is_child = 0 1.56.957.921 I slot print_timing: id 0 | task 7378 | prompt eval time = 125.30 ms / 422 tokens ( 0.30 ms per token, 3368.02 tokens per second) 1.56.957.927 I slot print_timing: id 0 | task 7378 | eval time = 1213.42 ms / 94 tokens ( 13.05 ms per token, 76.64 tokens per second) 1.56.957.928 I slot print_timing: id 0 | task 7378 | total time = 1338.72 ms / 516 tokens 1.56.957.929 I slot print_timing: id 0 | task 7378 | graphs reused = 7139 1.56.957.930 I slot print_timing: id 0 | task 7378 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.957.962 I slot release: id 0 | task 7378 | stop processing: n_tokens = 540, truncated = 0 1.56.983.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 116862129 1.56.983.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.819 MiB) 1.57.006.581 I slot launch_slot_: id 0 | task 7473 | processing task, is_child = 0 1.58.601.524 I slot print_timing: id 0 | task 7473 | prompt eval time = 141.75 ms / 499 tokens ( 0.28 ms per token, 3520.41 tokens per second) 1.58.601.529 I slot print_timing: id 0 | task 7473 | eval time = 1453.18 ms / 112 tokens ( 13.09 ms per token, 76.38 tokens per second) 1.58.601.530 I slot print_timing: id 0 | task 7473 | total time = 1594.93 ms / 611 tokens 1.58.601.531 I slot print_timing: id 0 | task 7473 | graphs reused = 7249 1.58.601.532 I slot print_timing: id 0 | task 7473 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.601.566 I slot release: id 0 | task 7473 | stop processing: n_tokens = 639, truncated = 0 1.58.617.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 118505733 1.58.617.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 1.58.643.357 I slot launch_slot_: id 0 | task 7586 | processing task, is_child = 0 1.59.305.631 I slot print_timing: id 0 | task 7586 | prompt eval time = 101.36 ms / 345 tokens ( 0.29 ms per token, 3403.71 tokens per second) 1.59.305.637 I slot print_timing: id 0 | task 7586 | eval time = 560.88 ms / 44 tokens ( 13.04 ms per token, 76.66 tokens per second) 1.59.305.639 I slot print_timing: id 0 | task 7586 | total time = 662.25 ms / 389 tokens 1.59.305.640 I slot print_timing: id 0 | task 7586 | graphs reused = 7291 1.59.305.641 I slot print_timing: id 0 | task 7586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.305.673 I slot release: id 0 | task 7586 | stop processing: n_tokens = 413, truncated = 0 1.59.321.268 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 119209840 1.59.321.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 1.59.339.746 I slot launch_slot_: id 0 | task 7631 | processing task, is_child = 0 2.00.001.956 I slot print_timing: id 0 | task 7631 | prompt eval time = 101.57 ms / 348 tokens ( 0.29 ms per token, 3426.14 tokens per second) 2.00.001.961 I slot print_timing: id 0 | task 7631 | eval time = 560.62 ms / 44 tokens ( 13.04 ms per token, 76.70 tokens per second) 2.00.001.962 I slot print_timing: id 0 | task 7631 | total time = 662.20 ms / 392 tokens 2.00.001.963 I slot print_timing: id 0 | task 7631 | graphs reused = 7333 2.00.001.964 I slot print_timing: id 0 | task 7631 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.001.993 I slot release: id 0 | task 7631 | stop processing: n_tokens = 416, truncated = 0 2.00.006.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 119906159 2.00.006.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 2.00.024.170 I slot launch_slot_: id 0 | task 7676 | processing task, is_child = 0 2.01.021.009 I slot print_timing: id 0 | task 7676 | prompt eval time = 124.61 ms / 408 tokens ( 0.31 ms per token, 3274.16 tokens per second) 2.01.021.015 I slot print_timing: id 0 | task 7676 | eval time = 872.21 ms / 68 tokens ( 13.02 ms per token, 76.82 tokens per second) 2.01.021.016 I slot print_timing: id 0 | task 7676 | total time = 996.82 ms / 476 tokens 2.01.021.017 I slot print_timing: id 0 | task 7676 | graphs reused = 7399 2.01.021.017 I slot print_timing: id 0 | task 7676 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.021.047 I slot release: id 0 | task 7676 | stop processing: n_tokens = 500, truncated = 0 2.01.041.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 120925213 2.01.041.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 2.01.062.665 I slot launch_slot_: id 0 | task 7745 | processing task, is_child = 0 2.01.989.667 I slot print_timing: id 0 | task 7745 | prompt eval time = 138.19 ms / 465 tokens ( 0.30 ms per token, 3365.03 tokens per second) 2.01.989.672 I slot print_timing: id 0 | task 7745 | eval time = 788.80 ms / 61 tokens ( 13.15 ms per token, 76.07 tokens per second) 2.01.989.673 I slot print_timing: id 0 | task 7745 | total time = 926.99 ms / 526 tokens 2.01.989.674 I slot print_timing: id 0 | task 7745 | graphs reused = 7457 2.01.989.675 I slot print_timing: id 0 | task 7745 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.989.706 I slot release: id 0 | task 7745 | stop processing: n_tokens = 550, truncated = 0 2.01.994.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 121893873 2.01.994.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 2.02.017.379 I slot launch_slot_: id 0 | task 7807 | processing task, is_child = 0 2.02.909.838 I slot print_timing: id 0 | task 7807 | prompt eval time = 124.23 ms / 399 tokens ( 0.31 ms per token, 3211.86 tokens per second) 2.02.909.843 I slot print_timing: id 0 | task 7807 | eval time = 768.22 ms / 60 tokens ( 13.02 ms per token, 76.80 tokens per second) 2.02.909.844 I slot print_timing: id 0 | task 7807 | total time = 892.44 ms / 459 tokens 2.02.909.845 I slot print_timing: id 0 | task 7807 | graphs reused = 7515 2.02.909.846 I slot print_timing: id 0 | task 7807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.909.879 I slot release: id 0 | task 7807 | stop processing: n_tokens = 500, truncated = 0 2.02.923.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 122814046 2.02.923.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 2.02.945.471 I slot launch_slot_: id 0 | task 7868 | processing task, is_child = 0 2.03.998.394 I slot print_timing: id 0 | task 7868 | prompt eval time = 125.41 ms / 419 tokens ( 0.30 ms per token, 3341.01 tokens per second) 2.03.998.399 I slot print_timing: id 0 | task 7868 | eval time = 927.50 ms / 72 tokens ( 13.06 ms per token, 76.55 tokens per second) 2.03.998.400 I slot print_timing: id 0 | task 7868 | total time = 1052.91 ms / 491 tokens 2.03.998.401 I slot print_timing: id 0 | task 7868 | graphs reused = 7584 2.03.998.402 I slot print_timing: id 0 | task 7868 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.998.434 I slot release: id 0 | task 7868 | stop processing: n_tokens = 515, truncated = 0 2.04.015.059 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 123902601 2.04.015.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 2.04.019.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 2.04.044.104 I slot launch_slot_: id 0 | task 7941 | processing task, is_child = 0 2.05.085.995 I slot print_timing: id 0 | task 7941 | prompt eval time = 125.69 ms / 440 tokens ( 0.29 ms per token, 3500.54 tokens per second) 2.05.086.001 I slot print_timing: id 0 | task 7941 | eval time = 916.18 ms / 71 tokens ( 13.09 ms per token, 76.40 tokens per second) 2.05.086.002 I slot print_timing: id 0 | task 7941 | total time = 1041.88 ms / 511 tokens 2.05.086.003 I slot print_timing: id 0 | task 7941 | graphs reused = 7652 2.05.086.004 I slot print_timing: id 0 | task 7941 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.086.036 I slot release: id 0 | task 7941 | stop processing: n_tokens = 535, truncated = 0 2.05.110.708 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 124990203 2.05.110.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.506 MiB) 2.05.132.663 I slot launch_slot_: id 0 | task 8013 | processing task, is_child = 0 2.05.899.882 I slot print_timing: id 0 | task 8013 | prompt eval time = 101.44 ms / 372 tokens ( 0.27 ms per token, 3667.23 tokens per second) 2.05.899.888 I slot print_timing: id 0 | task 8013 | eval time = 665.76 ms / 52 tokens ( 13.05 ms per token, 76.60 tokens per second) 2.05.899.890 I slot print_timing: id 0 | task 8013 | total time = 767.20 ms / 424 tokens 2.05.899.890 I slot print_timing: id 0 | task 8013 | graphs reused = 7702 2.05.899.892 I slot print_timing: id 0 | task 8013 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.899.925 I slot release: id 0 | task 8013 | stop processing: n_tokens = 448, truncated = 0 2.05.920.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 125804092 2.05.920.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 2.05.940.169 I slot launch_slot_: id 0 | task 8066 | processing task, is_child = 0 2.06.826.306 I slot print_timing: id 0 | task 8066 | prompt eval time = 138.47 ms / 449 tokens ( 0.31 ms per token, 3242.53 tokens per second) 2.06.826.311 I slot print_timing: id 0 | task 8066 | eval time = 747.65 ms / 58 tokens ( 13.12 ms per token, 76.24 tokens per second) 2.06.826.312 I slot print_timing: id 0 | task 8066 | total time = 886.12 ms / 507 tokens 2.06.826.313 I slot print_timing: id 0 | task 8066 | graphs reused = 7757 2.06.826.314 I slot print_timing: id 0 | task 8066 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.826.358 I slot release: id 0 | task 8066 | stop processing: n_tokens = 531, truncated = 0 2.06.844.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 126730525 2.06.845.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 2.06.866.772 I slot launch_slot_: id 0 | task 8125 | processing task, is_child = 0 2.07.762.165 I slot print_timing: id 0 | task 8125 | prompt eval time = 101.85 ms / 360 tokens ( 0.28 ms per token, 3534.47 tokens per second) 2.07.762.171 I slot print_timing: id 0 | task 8125 | eval time = 793.52 ms / 62 tokens ( 13.01 ms per token, 76.87 tokens per second) 2.07.762.171 I slot print_timing: id 0 | task 8125 | total time = 895.38 ms / 422 tokens 2.07.762.172 I slot print_timing: id 0 | task 8125 | graphs reused = 7817 2.07.762.173 I slot print_timing: id 0 | task 8125 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.762.203 I slot release: id 0 | task 8125 | stop processing: n_tokens = 446, truncated = 0 2.07.781.254 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 127666370 2.07.781.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 2.07.801.041 I slot launch_slot_: id 0 | task 8188 | processing task, is_child = 0 2.08.619.473 I slot print_timing: id 0 | task 8188 | prompt eval time = 101.55 ms / 346 tokens ( 0.29 ms per token, 3407.26 tokens per second) 2.08.619.479 I slot print_timing: id 0 | task 8188 | eval time = 716.87 ms / 55 tokens ( 13.28 ms per token, 75.33 tokens per second) 2.08.619.480 I slot print_timing: id 0 | task 8188 | total time = 818.41 ms / 401 tokens 2.08.619.480 I slot print_timing: id 0 | task 8188 | graphs reused = 7870 2.08.619.481 I slot print_timing: id 0 | task 8188 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.619.510 I slot release: id 0 | task 8188 | stop processing: n_tokens = 425, truncated = 0 2.08.623.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 128523677 2.08.623.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 2.08.644.925 I slot launch_slot_: id 0 | task 8244 | processing task, is_child = 0 2.09.434.852 I slot print_timing: id 0 | task 8244 | prompt eval time = 126.27 ms / 434 tokens ( 0.29 ms per token, 3436.97 tokens per second) 2.09.434.858 I slot print_timing: id 0 | task 8244 | eval time = 663.64 ms / 52 tokens ( 13.01 ms per token, 76.85 tokens per second) 2.09.434.859 I slot print_timing: id 0 | task 8244 | total time = 789.91 ms / 486 tokens 2.09.434.859 I slot print_timing: id 0 | task 8244 | graphs reused = 7920 2.09.434.860 I slot print_timing: id 0 | task 8244 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.434.893 I slot release: id 0 | task 8244 | stop processing: n_tokens = 510, truncated = 0 2.09.459.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 129339060 2.09.459.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 2.09.463.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 2.09.485.551 I slot launch_slot_: id 0 | task 8297 | processing task, is_child = 0 2.10.359.776 I slot print_timing: id 0 | task 8297 | prompt eval time = 101.26 ms / 369 tokens ( 0.27 ms per token, 3644.12 tokens per second) 2.10.359.781 I slot print_timing: id 0 | task 8297 | eval time = 772.95 ms / 59 tokens ( 13.33 ms per token, 75.04 tokens per second) 2.10.359.782 I slot print_timing: id 0 | task 8297 | total time = 874.21 ms / 428 tokens 2.10.359.783 I slot print_timing: id 0 | task 8297 | graphs reused = 7977 2.10.359.784 I slot print_timing: id 0 | task 8297 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.359.814 I slot release: id 0 | task 8297 | stop processing: n_tokens = 452, truncated = 0 2.10.385.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 130263981 2.10.400.999 I slot launch_slot_: id 0 | task 8357 | processing task, is_child = 0 2.11.534.280 I slot print_timing: id 0 | task 8357 | prompt eval time = 126.28 ms / 446 tokens ( 0.28 ms per token, 3531.83 tokens per second) 2.11.534.285 I slot print_timing: id 0 | task 8357 | eval time = 1006.98 ms / 78 tokens ( 13.08 ms per token, 76.47 tokens per second) 2.11.534.286 I slot print_timing: id 0 | task 8357 | total time = 1133.26 ms / 524 tokens 2.11.534.287 I slot print_timing: id 0 | task 8357 | graphs reused = 8052 2.11.534.288 I slot print_timing: id 0 | task 8357 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.534.321 I slot release: id 0 | task 8357 | stop processing: n_tokens = 548, truncated = 0 2.11.562.060 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 131438488 2.11.562.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 2.11.566.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 2.11.589.522 I slot launch_slot_: id 0 | task 8436 | processing task, is_child = 0 2.12.324.977 I slot print_timing: id 0 | task 8436 | prompt eval time = 123.89 ms / 396 tokens ( 0.31 ms per token, 3196.36 tokens per second) 2.12.324.983 I slot print_timing: id 0 | task 8436 | eval time = 611.55 ms / 48 tokens ( 13.01 ms per token, 76.85 tokens per second) 2.12.324.984 I slot print_timing: id 0 | task 8436 | total time = 735.44 ms / 444 tokens 2.12.324.985 I slot print_timing: id 0 | task 8436 | graphs reused = 8098 2.12.324.985 I slot print_timing: id 0 | task 8436 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.325.018 I slot release: id 0 | task 8436 | stop processing: n_tokens = 470, truncated = 0 2.12.354.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 132229185 2.12.354.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.288 MiB) 2.12.374.829 I slot launch_slot_: id 0 | task 8485 | processing task, is_child = 0 2.13.651.659 I slot print_timing: id 0 | task 8485 | prompt eval time = 138.38 ms / 466 tokens ( 0.30 ms per token, 3367.42 tokens per second) 2.13.651.664 I slot print_timing: id 0 | task 8485 | eval time = 1138.43 ms / 88 tokens ( 13.09 ms per token, 76.42 tokens per second) 2.13.651.666 I slot print_timing: id 0 | task 8485 | total time = 1276.82 ms / 554 tokens 2.13.651.667 I slot print_timing: id 0 | task 8485 | graphs reused = 8183 2.13.651.668 I slot print_timing: id 0 | task 8485 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.651.699 I slot release: id 0 | task 8485 | stop processing: n_tokens = 578, truncated = 0 2.13.665.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 133555866 2.13.665.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 2.13.688.797 I slot launch_slot_: id 0 | task 8574 | processing task, is_child = 0 2.14.698.411 I slot print_timing: id 0 | task 8574 | prompt eval time = 138.52 ms / 467 tokens ( 0.30 ms per token, 3371.33 tokens per second) 2.14.698.417 I slot print_timing: id 0 | task 8574 | eval time = 871.08 ms / 66 tokens ( 13.40 ms per token, 74.62 tokens per second) 2.14.698.418 I slot print_timing: id 0 | task 8574 | total time = 1009.60 ms / 533 tokens 2.14.698.419 I slot print_timing: id 0 | task 8574 | graphs reused = 8246 2.14.698.420 I slot print_timing: id 0 | task 8574 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.698.454 I slot release: id 0 | task 8574 | stop processing: n_tokens = 557, truncated = 0 2.14.713.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 134602621 2.14.713.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 2.14.735.839 I slot launch_slot_: id 0 | task 8641 | processing task, is_child = 0 2.15.798.733 I slot print_timing: id 0 | task 8641 | prompt eval time = 138.42 ms / 454 tokens ( 0.30 ms per token, 3279.78 tokens per second) 2.15.798.738 I slot print_timing: id 0 | task 8641 | eval time = 924.45 ms / 71 tokens ( 13.21 ms per token, 75.72 tokens per second) 2.15.798.739 I slot print_timing: id 0 | task 8641 | total time = 1062.88 ms / 525 tokens 2.15.798.741 I slot print_timing: id 0 | task 8641 | graphs reused = 8314 2.15.798.741 I slot print_timing: id 0 | task 8641 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.798.776 I slot release: id 0 | task 8641 | stop processing: n_tokens = 549, truncated = 0 2.15.802.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 135702942 2.15.802.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 2.15.825.369 I slot launch_slot_: id 0 | task 8713 | processing task, is_child = 0 2.16.742.703 I slot print_timing: id 0 | task 8713 | prompt eval time = 124.70 ms / 409 tokens ( 0.30 ms per token, 3279.98 tokens per second) 2.16.742.709 I slot print_timing: id 0 | task 8713 | eval time = 792.62 ms / 62 tokens ( 12.99 ms per token, 76.96 tokens per second) 2.16.742.710 I slot print_timing: id 0 | task 8713 | total time = 917.32 ms / 471 tokens 2.16.742.711 I slot print_timing: id 0 | task 8713 | graphs reused = 8374 2.16.742.712 I slot print_timing: id 0 | task 8713 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.742.743 I slot release: id 0 | task 8713 | stop processing: n_tokens = 495, truncated = 0 2.16.746.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 136646910 2.16.746.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 2.16.769.040 I slot launch_slot_: id 0 | task 8776 | processing task, is_child = 0 2.17.599.317 I slot print_timing: id 0 | task 8776 | prompt eval time = 101.48 ms / 349 tokens ( 0.29 ms per token, 3439.14 tokens per second) 2.17.599.323 I slot print_timing: id 0 | task 8776 | eval time = 728.78 ms / 57 tokens ( 13.01 ms per token, 76.84 tokens per second) 2.17.599.325 I slot print_timing: id 0 | task 8776 | total time = 830.26 ms / 406 tokens 2.17.599.325 I slot print_timing: id 0 | task 8776 | graphs reused = 8429 2.17.599.327 I slot print_timing: id 0 | task 8776 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.599.356 I slot release: id 0 | task 8776 | stop processing: n_tokens = 430, truncated = 0 2.17.616.102 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 137503523 2.17.616.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 2.17.635.062 I slot launch_slot_: id 0 | task 8834 | processing task, is_child = 0 2.18.507.344 I slot print_timing: id 0 | task 8834 | prompt eval time = 125.87 ms / 435 tokens ( 0.29 ms per token, 3455.84 tokens per second) 2.18.507.350 I slot print_timing: id 0 | task 8834 | eval time = 746.39 ms / 58 tokens ( 13.09 ms per token, 76.37 tokens per second) 2.18.507.351 I slot print_timing: id 0 | task 8834 | total time = 872.26 ms / 493 tokens 2.18.507.352 I slot print_timing: id 0 | task 8834 | graphs reused = 8484 2.18.507.353 I slot print_timing: id 0 | task 8834 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.507.385 I slot release: id 0 | task 8834 | stop processing: n_tokens = 517, truncated = 0 2.18.535.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 138411551 2.18.535.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 2.18.539.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 2.18.561.506 I slot launch_slot_: id 0 | task 8893 | processing task, is_child = 0 2.19.269.597 I slot print_timing: id 0 | task 8893 | prompt eval time = 91.95 ms / 322 tokens ( 0.29 ms per token, 3501.98 tokens per second) 2.19.269.602 I slot print_timing: id 0 | task 8893 | eval time = 616.13 ms / 47 tokens ( 13.39 ms per token, 74.66 tokens per second) 2.19.269.603 I slot print_timing: id 0 | task 8893 | total time = 708.07 ms / 369 tokens 2.19.269.604 I slot print_timing: id 0 | task 8893 | graphs reused = 8529 2.19.269.605 I slot print_timing: id 0 | task 8893 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.269.631 I slot release: id 0 | task 8893 | stop processing: n_tokens = 393, truncated = 0 2.19.290.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 139173798 2.19.290.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 2.19.309.104 I slot launch_slot_: id 0 | task 8941 | processing task, is_child = 0 2.20.125.922 I slot print_timing: id 0 | task 8941 | prompt eval time = 101.95 ms / 360 tokens ( 0.28 ms per token, 3531.25 tokens per second) 2.20.125.928 I slot print_timing: id 0 | task 8941 | eval time = 714.86 ms / 56 tokens ( 13.00 ms per token, 76.94 tokens per second) 2.20.125.929 I slot print_timing: id 0 | task 8941 | total time = 816.80 ms / 416 tokens 2.20.125.930 I slot print_timing: id 0 | task 8941 | graphs reused = 8583 2.20.125.931 I slot print_timing: id 0 | task 8941 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.125.960 I slot release: id 0 | task 8941 | stop processing: n_tokens = 440, truncated = 0 2.20.151.376 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 140030127 2.20.151.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 2.20.171.494 I slot launch_slot_: id 0 | task 8998 | processing task, is_child = 0 2.21.238.991 I slot print_timing: id 0 | task 8998 | prompt eval time = 125.81 ms / 443 tokens ( 0.28 ms per token, 3521.18 tokens per second) 2.21.238.996 I slot print_timing: id 0 | task 8998 | eval time = 941.67 ms / 73 tokens ( 13.08 ms per token, 76.46 tokens per second) 2.21.238.997 I slot print_timing: id 0 | task 8998 | total time = 1067.48 ms / 516 tokens 2.21.238.998 I slot print_timing: id 0 | task 8998 | graphs reused = 8653 2.21.238.998 I slot print_timing: id 0 | task 8998 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.239.028 I slot release: id 0 | task 8998 | stop processing: n_tokens = 540, truncated = 0 2.21.267.254 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 141143195 2.21.267.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 2.21.289.393 I slot launch_slot_: id 0 | task 9072 | processing task, is_child = 0 2.21.975.071 I slot print_timing: id 0 | task 9072 | prompt eval time = 125.68 ms / 442 tokens ( 0.28 ms per token, 3516.84 tokens per second) 2.21.975.077 I slot print_timing: id 0 | task 9072 | eval time = 559.98 ms / 44 tokens ( 13.02 ms per token, 76.79 tokens per second) 2.21.975.078 I slot print_timing: id 0 | task 9072 | total time = 685.66 ms / 486 tokens 2.21.975.079 I slot print_timing: id 0 | task 9072 | graphs reused = 8695 2.21.975.080 I slot print_timing: id 0 | task 9072 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.975.110 I slot release: id 0 | task 9072 | stop processing: n_tokens = 510, truncated = 0 2.21.997.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 141879277 2.21.997.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 2.22.018.783 I slot launch_slot_: id 0 | task 9117 | processing task, is_child = 0 2.22.723.827 I slot print_timing: id 0 | task 9117 | prompt eval time = 138.71 ms / 470 tokens ( 0.30 ms per token, 3388.49 tokens per second) 2.22.723.833 I slot print_timing: id 0 | task 9117 | eval time = 566.32 ms / 44 tokens ( 13.17 ms per token, 75.93 tokens per second) 2.22.723.834 I slot print_timing: id 0 | task 9117 | total time = 705.03 ms / 514 tokens 2.22.723.835 I slot print_timing: id 0 | task 9117 | graphs reused = 8736 2.22.723.836 I slot print_timing: id 0 | task 9117 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.723.869 I slot release: id 0 | task 9117 | stop processing: n_tokens = 538, truncated = 0 2.22.744.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 142628036 2.22.744.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 2.22.766.789 I slot launch_slot_: id 0 | task 9162 | processing task, is_child = 0 2.23.344.011 I slot print_timing: id 0 | task 9162 | prompt eval time = 139.64 ms / 483 tokens ( 0.29 ms per token, 3458.92 tokens per second) 2.23.344.016 I slot print_timing: id 0 | task 9162 | eval time = 437.57 ms / 34 tokens ( 13.26 ms per token, 75.42 tokens per second) 2.23.344.017 I slot print_timing: id 0 | task 9162 | total time = 577.20 ms / 517 tokens 2.23.344.018 I slot print_timing: id 0 | task 9162 | graphs reused = 8767 2.23.344.019 I slot print_timing: id 0 | task 9162 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.344.053 I slot release: id 0 | task 9162 | stop processing: n_tokens = 541, truncated = 0 2.23.360.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 143248220 2.23.360.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 2.23.364.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 2.23.386.123 I slot launch_slot_: id 0 | task 9197 | processing task, is_child = 0 2.24.232.828 I slot print_timing: id 0 | task 9197 | prompt eval time = 138.32 ms / 463 tokens ( 0.30 ms per token, 3347.38 tokens per second) 2.24.232.834 I slot print_timing: id 0 | task 9197 | eval time = 708.37 ms / 55 tokens ( 13.12 ms per token, 76.23 tokens per second) 2.24.232.835 I slot print_timing: id 0 | task 9197 | total time = 846.69 ms / 518 tokens 2.24.232.836 I slot print_timing: id 0 | task 9197 | graphs reused = 8819 2.24.232.837 I slot print_timing: id 0 | task 9197 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.232.867 I slot release: id 0 | task 9197 | stop processing: n_tokens = 542, truncated = 0 2.24.237.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 144137034 2.24.237.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 2.24.260.526 I slot launch_slot_: id 0 | task 9253 | processing task, is_child = 0 2.25.022.771 I slot print_timing: id 0 | task 9253 | prompt eval time = 125.14 ms / 421 tokens ( 0.30 ms per token, 3364.34 tokens per second) 2.25.022.777 I slot print_timing: id 0 | task 9253 | eval time = 637.09 ms / 50 tokens ( 13.00 ms per token, 76.91 tokens per second) 2.25.022.778 I slot print_timing: id 0 | task 9253 | total time = 762.23 ms / 471 tokens 2.25.022.779 I slot print_timing: id 0 | task 9253 | graphs reused = 8867 2.25.022.780 I slot print_timing: id 0 | task 9253 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.022.809 I slot release: id 0 | task 9253 | stop processing: n_tokens = 495, truncated = 0 2.25.037.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 144926976 2.25.037.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 2.25.058.923 I slot launch_slot_: id 0 | task 9304 | processing task, is_child = 0 2.25.708.614 I slot print_timing: id 0 | task 9304 | prompt eval time = 102.05 ms / 360 tokens ( 0.28 ms per token, 3527.79 tokens per second) 2.25.708.619 I slot print_timing: id 0 | task 9304 | eval time = 547.63 ms / 43 tokens ( 13.04 ms per token, 76.69 tokens per second) 2.25.708.620 I slot print_timing: id 0 | task 9304 | total time = 649.68 ms / 403 tokens 2.25.708.621 I slot print_timing: id 0 | task 9304 | graphs reused = 8908 2.25.708.622 I slot print_timing: id 0 | task 9304 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.708.651 I slot release: id 0 | task 9304 | stop processing: n_tokens = 427, truncated = 0 2.25.736.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 145612817 2.25.736.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.664 MiB) 2.25.757.974 I slot launch_slot_: id 0 | task 9348 | processing task, is_child = 0 2.26.813.098 I slot print_timing: id 0 | task 9348 | prompt eval time = 164.50 ms / 547 tokens ( 0.30 ms per token, 3325.21 tokens per second) 2.26.813.104 I slot print_timing: id 0 | task 9348 | eval time = 890.61 ms / 69 tokens ( 13.10 ms per token, 76.35 tokens per second) 2.26.813.106 I slot print_timing: id 0 | task 9348 | total time = 1055.11 ms / 616 tokens 2.26.813.106 I slot print_timing: id 0 | task 9348 | graphs reused = 8975 2.26.813.107 I slot print_timing: id 0 | task 9348 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.813.143 I slot release: id 0 | task 9348 | stop processing: n_tokens = 640, truncated = 0 2.26.843.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 146717310 2.26.843.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 2.26.868.302 I slot launch_slot_: id 0 | task 9418 | processing task, is_child = 0 2.28.471.731 I slot print_timing: id 0 | task 9418 | prompt eval time = 216.36 ms / 749 tokens ( 0.29 ms per token, 3461.82 tokens per second) 2.28.471.736 I slot print_timing: id 0 | task 9418 | eval time = 1387.05 ms / 107 tokens ( 13.09 ms per token, 76.42 tokens per second) 2.28.471.738 I slot print_timing: id 0 | task 9418 | total time = 1603.41 ms / 856 tokens 2.28.471.739 I slot print_timing: id 0 | task 9418 | graphs reused = 9080 2.28.471.739 I slot print_timing: id 0 | task 9418 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.471.780 I slot release: id 0 | task 9418 | stop processing: n_tokens = 880, truncated = 0 2.28.498.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 148375946 2.28.498.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 2.28.502.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 2.28.534.888 I slot launch_slot_: id 0 | task 9526 | processing task, is_child = 0 2.29.349.598 I slot print_timing: id 0 | task 9526 | prompt eval time = 198.57 ms / 678 tokens ( 0.29 ms per token, 3414.45 tokens per second) 2.29.349.604 I slot print_timing: id 0 | task 9526 | eval time = 616.12 ms / 48 tokens ( 13.11 ms per token, 76.28 tokens per second) 2.29.349.605 I slot print_timing: id 0 | task 9526 | total time = 814.69 ms / 726 tokens 2.29.349.605 I slot print_timing: id 0 | task 9526 | graphs reused = 9126 2.29.349.606 I slot print_timing: id 0 | task 9526 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.349.646 I slot release: id 0 | task 9526 | stop processing: n_tokens = 750, truncated = 0 2.29.371.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 149253813 2.29.371.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.29.376.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 2.29.404.936 I slot launch_slot_: id 0 | task 9575 | processing task, is_child = 0 2.30.312.362 I slot print_timing: id 0 | task 9575 | prompt eval time = 165.86 ms / 567 tokens ( 0.29 ms per token, 3418.55 tokens per second) 2.30.312.368 I slot print_timing: id 0 | task 9575 | eval time = 741.55 ms / 57 tokens ( 13.24 ms per token, 75.52 tokens per second) 2.30.312.369 I slot print_timing: id 0 | task 9575 | total time = 907.41 ms / 624 tokens 2.30.312.370 I slot print_timing: id 0 | task 9575 | graphs reused = 9181 2.30.312.371 I slot print_timing: id 0 | task 9575 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.312.408 I slot release: id 0 | task 9575 | stop processing: n_tokens = 648, truncated = 0 2.30.335.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 150216575 2.30.335.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.30.339.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 2.30.364.494 I slot launch_slot_: id 0 | task 9633 | processing task, is_child = 0 2.31.251.474 I slot print_timing: id 0 | task 9633 | prompt eval time = 141.31 ms / 501 tokens ( 0.28 ms per token, 3545.32 tokens per second) 2.31.251.480 I slot print_timing: id 0 | task 9633 | eval time = 745.65 ms / 58 tokens ( 13.08 ms per token, 76.44 tokens per second) 2.31.251.481 I slot print_timing: id 0 | task 9633 | total time = 886.96 ms / 559 tokens 2.31.251.482 I slot print_timing: id 0 | task 9633 | graphs reused = 9237 2.31.251.483 I slot print_timing: id 0 | task 9633 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.251.515 I slot release: id 0 | task 9633 | stop processing: n_tokens = 583, truncated = 0 2.31.271.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 151155682 2.31.271.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 2.31.293.683 I slot launch_slot_: id 0 | task 9692 | processing task, is_child = 0 2.32.315.706 I slot print_timing: id 0 | task 9692 | prompt eval time = 221.64 ms / 769 tokens ( 0.29 ms per token, 3469.53 tokens per second) 2.32.315.712 I slot print_timing: id 0 | task 9692 | eval time = 800.36 ms / 62 tokens ( 13.12 ms per token, 76.22 tokens per second) 2.32.315.713 I slot print_timing: id 0 | task 9692 | total time = 1022.01 ms / 831 tokens 2.32.315.714 I slot print_timing: id 0 | task 9692 | graphs reused = 9297 2.32.315.715 I slot print_timing: id 0 | task 9692 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.315.758 I slot release: id 0 | task 9692 | stop processing: n_tokens = 855, truncated = 0 2.32.337.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 152219924 2.32.337.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 2.32.341.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.32.372.173 I slot launch_slot_: id 0 | task 9755 | processing task, is_child = 0 2.33.299.115 I slot print_timing: id 0 | task 9755 | prompt eval time = 141.44 ms / 500 tokens ( 0.28 ms per token, 3534.97 tokens per second) 2.33.299.121 I slot print_timing: id 0 | task 9755 | eval time = 785.48 ms / 61 tokens ( 13.09 ms per token, 76.39 tokens per second) 2.33.299.122 I slot print_timing: id 0 | task 9755 | total time = 926.93 ms / 561 tokens 2.33.299.123 I slot print_timing: id 0 | task 9755 | graphs reused = 9356 2.33.299.123 I slot print_timing: id 0 | task 9755 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.299.157 I slot release: id 0 | task 9755 | stop processing: n_tokens = 585, truncated = 0 2.33.321.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 153203323 2.33.321.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 2.33.346.060 I slot launch_slot_: id 0 | task 9817 | processing task, is_child = 0 2.34.282.161 I slot print_timing: id 0 | task 9817 | prompt eval time = 180.92 ms / 632 tokens ( 0.29 ms per token, 3493.22 tokens per second) 2.34.282.166 I slot print_timing: id 0 | task 9817 | eval time = 755.16 ms / 58 tokens ( 13.25 ms per token, 75.48 tokens per second) 2.34.282.167 I slot print_timing: id 0 | task 9817 | total time = 936.09 ms / 690 tokens 2.34.282.168 I slot print_timing: id 0 | task 9817 | graphs reused = 9412 2.34.282.169 I slot print_timing: id 0 | task 9817 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.282.207 I slot release: id 0 | task 9817 | stop processing: n_tokens = 714, truncated = 0 2.34.286.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 154186374 2.34.287.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 2.34.323.825 I slot launch_slot_: id 0 | task 9876 | processing task, is_child = 0 2.34.917.287 I slot print_timing: id 0 | task 9876 | prompt eval time = 124.08 ms / 395 tokens ( 0.31 ms per token, 3183.30 tokens per second) 2.34.917.293 I slot print_timing: id 0 | task 9876 | eval time = 469.36 ms / 37 tokens ( 13.04 ms per token, 76.70 tokens per second) 2.34.917.294 I slot print_timing: id 0 | task 9876 | total time = 593.45 ms / 432 tokens 2.34.917.295 I slot print_timing: id 0 | task 9876 | graphs reused = 9447 2.34.917.296 I slot print_timing: id 0 | task 9876 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.917.326 I slot release: id 0 | task 9876 | stop processing: n_tokens = 456, truncated = 0 2.34.935.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 154821493 2.34.935.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 2.34.955.521 I slot launch_slot_: id 0 | task 9914 | processing task, is_child = 0 2.35.906.483 I slot print_timing: id 0 | task 9914 | prompt eval time = 171.04 ms / 579 tokens ( 0.30 ms per token, 3385.13 tokens per second) 2.35.906.489 I slot print_timing: id 0 | task 9914 | eval time = 779.90 ms / 59 tokens ( 13.45 ms per token, 74.37 tokens per second) 2.35.906.490 I slot print_timing: id 0 | task 9914 | total time = 950.95 ms / 638 tokens 2.35.906.491 I slot print_timing: id 0 | task 9914 | graphs reused = 9504 2.35.906.492 I slot print_timing: id 0 | task 9914 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.906.529 I slot release: id 0 | task 9914 | stop processing: n_tokens = 662, truncated = 0 2.35.933.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 155810696 2.35.933.093 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 2.35.937.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 2.35.963.463 I slot launch_slot_: id 0 | task 9974 | processing task, is_child = 0 2.36.760.405 I slot print_timing: id 0 | task 9974 | prompt eval time = 197.91 ms / 689 tokens ( 0.29 ms per token, 3481.40 tokens per second) 2.36.760.410 I slot print_timing: id 0 | task 9974 | eval time = 599.01 ms / 46 tokens ( 13.31 ms per token, 75.12 tokens per second) 2.36.760.411 I slot print_timing: id 0 | task 9974 | total time = 796.92 ms / 735 tokens 2.36.760.412 I slot print_timing: id 0 | task 9974 | graphs reused = 9548 2.36.760.413 I slot print_timing: id 0 | task 9974 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.760.455 I slot release: id 0 | task 9974 | stop processing: n_tokens = 759, truncated = 0 2.36.777.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 156664622 2.36.777.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 2.36.808.273 I slot launch_slot_: id 0 | task 10021 | processing task, is_child = 0 2.37.882.257 I slot print_timing: id 0 | task 10021 | prompt eval time = 212.76 ms / 752 tokens ( 0.28 ms per token, 3534.43 tokens per second) 2.37.882.263 I slot print_timing: id 0 | task 10021 | eval time = 861.20 ms / 66 tokens ( 13.25 ms per token, 75.48 tokens per second) 2.37.882.264 I slot print_timing: id 0 | task 10021 | total time = 1073.97 ms / 818 tokens 2.37.882.265 I slot print_timing: id 0 | task 10021 | graphs reused = 9612 2.37.882.266 I slot print_timing: id 0 | task 10021 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.882.307 I slot release: id 0 | task 10021 | stop processing: n_tokens = 842, truncated = 0 2.37.905.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 157786474 2.37.905.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 2.37.911.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.37.944.277 I slot launch_slot_: id 0 | task 10088 | processing task, is_child = 0 2.38.977.876 I slot print_timing: id 0 | task 10088 | prompt eval time = 170.72 ms / 582 tokens ( 0.29 ms per token, 3409.17 tokens per second) 2.38.977.882 I slot print_timing: id 0 | task 10088 | eval time = 862.87 ms / 67 tokens ( 13.07 ms per token, 76.49 tokens per second) 2.38.977.883 I slot print_timing: id 0 | task 10088 | total time = 1033.58 ms / 649 tokens 2.38.977.884 I slot print_timing: id 0 | task 10088 | graphs reused = 9677 2.38.977.885 I slot print_timing: id 0 | task 10088 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.977.921 I slot release: id 0 | task 10088 | stop processing: n_tokens = 673, truncated = 0 2.38.994.684 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 158882087 2.38.994.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 2.39.024.791 I slot launch_slot_: id 0 | task 10156 | processing task, is_child = 0 2.40.209.937 I slot print_timing: id 0 | task 10156 | prompt eval time = 191.69 ms / 656 tokens ( 0.29 ms per token, 3422.25 tokens per second) 2.40.209.943 I slot print_timing: id 0 | task 10156 | eval time = 993.44 ms / 77 tokens ( 13.07 ms per token, 76.50 tokens per second) 2.40.209.944 I slot print_timing: id 0 | task 10156 | total time = 1185.13 ms / 733 tokens 2.40.209.945 I slot print_timing: id 0 | task 10156 | graphs reused = 9752 2.40.209.946 I slot print_timing: id 0 | task 10156 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.209.985 I slot release: id 0 | task 10156 | stop processing: n_tokens = 757, truncated = 0 2.40.215.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 160114152 2.40.215.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.728 MiB) 2.40.254.637 I slot launch_slot_: id 0 | task 10234 | processing task, is_child = 0 2.40.827.413 I slot print_timing: id 0 | task 10234 | prompt eval time = 177.98 ms / 613 tokens ( 0.29 ms per token, 3444.13 tokens per second) 2.40.827.419 I slot print_timing: id 0 | task 10234 | eval time = 394.77 ms / 31 tokens ( 13.16 ms per token, 75.99 tokens per second) 2.40.827.420 I slot print_timing: id 0 | task 10234 | total time = 572.76 ms / 644 tokens 2.40.827.420 I slot print_timing: id 0 | task 10234 | graphs reused = 9781 2.40.827.421 I slot print_timing: id 0 | task 10234 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.827.458 I slot release: id 0 | task 10234 | stop processing: n_tokens = 668, truncated = 0 2.40.847.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 160731624 2.40.847.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.40.874.571 I slot launch_slot_: id 0 | task 10266 | processing task, is_child = 0 2.42.354.562 I slot print_timing: id 0 | task 10266 | prompt eval time = 213.22 ms / 766 tokens ( 0.28 ms per token, 3592.53 tokens per second) 2.42.354.568 I slot print_timing: id 0 | task 10266 | eval time = 1266.76 ms / 97 tokens ( 13.20 ms per token, 75.78 tokens per second) 2.42.354.569 I slot print_timing: id 0 | task 10266 | total time = 1479.98 ms / 863 tokens 2.42.354.570 I slot print_timing: id 0 | task 10266 | graphs reused = 9876 2.42.354.571 I slot print_timing: id 0 | task 10266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.354.614 I slot release: id 0 | task 10266 | stop processing: n_tokens = 887, truncated = 0 2.42.377.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 162258781 2.42.377.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.415 MiB) 2.42.417.044 I slot launch_slot_: id 0 | task 10364 | processing task, is_child = 0 2.43.435.783 I slot print_timing: id 0 | task 10364 | prompt eval time = 231.94 ms / 846 tokens ( 0.27 ms per token, 3647.43 tokens per second) 2.43.435.789 I slot print_timing: id 0 | task 10364 | eval time = 786.78 ms / 61 tokens ( 13.11 ms per token, 76.26 tokens per second) 2.43.435.790 I slot print_timing: id 0 | task 10364 | total time = 1018.72 ms / 907 tokens 2.43.435.791 I slot print_timing: id 0 | task 10364 | graphs reused = 9935 2.43.435.792 I slot print_timing: id 0 | task 10364 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.435.844 I slot release: id 0 | task 10364 | stop processing: n_tokens = 931, truncated = 0 2.43.452.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 163340011 2.43.452.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 2.43.459.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 2.43.499.948 I slot launch_slot_: id 0 | task 10426 | processing task, is_child = 0 2.44.696.672 I slot print_timing: id 0 | task 10426 | prompt eval time = 200.19 ms / 650 tokens ( 0.31 ms per token, 3246.85 tokens per second) 2.44.696.677 I slot print_timing: id 0 | task 10426 | eval time = 996.51 ms / 77 tokens ( 13.11 ms per token, 76.27 tokens per second) 2.44.696.679 I slot print_timing: id 0 | task 10426 | total time = 1196.70 ms / 727 tokens 2.44.696.679 I slot print_timing: id 0 | task 10426 | graphs reused = 10010 2.44.696.680 I slot print_timing: id 0 | task 10426 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.696.722 I slot release: id 0 | task 10426 | stop processing: n_tokens = 751, truncated = 0 2.44.720.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 164600889 2.44.721.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.507 MiB) 2.44.751.509 I slot launch_slot_: id 0 | task 10504 | processing task, is_child = 0 2.45.644.170 I slot print_timing: id 0 | task 10504 | prompt eval time = 205.43 ms / 717 tokens ( 0.29 ms per token, 3490.24 tokens per second) 2.45.644.178 I slot print_timing: id 0 | task 10504 | eval time = 687.21 ms / 53 tokens ( 13.22 ms per token, 75.67 tokens per second) 2.45.644.179 I slot print_timing: id 0 | task 10504 | total time = 892.64 ms / 770 tokens 2.45.644.180 I slot print_timing: id 0 | task 10504 | graphs reused = 10060 2.45.644.180 I slot print_timing: id 0 | task 10504 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.644.222 I slot release: id 0 | task 10504 | stop processing: n_tokens = 794, truncated = 0 2.45.665.514 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 165548389 2.45.665.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 2.45.697.145 I slot launch_slot_: id 0 | task 10558 | processing task, is_child = 0 2.46.598.426 I slot print_timing: id 0 | task 10558 | prompt eval time = 141.27 ms / 494 tokens ( 0.29 ms per token, 3496.95 tokens per second) 2.46.598.432 I slot print_timing: id 0 | task 10558 | eval time = 760.00 ms / 59 tokens ( 13.10 ms per token, 76.32 tokens per second) 2.46.598.433 I slot print_timing: id 0 | task 10558 | total time = 901.26 ms / 553 tokens 2.46.598.434 I slot print_timing: id 0 | task 10558 | graphs reused = 10117 2.46.598.435 I slot print_timing: id 0 | task 10558 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.598.468 I slot release: id 0 | task 10558 | stop processing: n_tokens = 577, truncated = 0 2.46.615.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 166502635 2.46.615.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.883 MiB) 2.46.641.075 I slot launch_slot_: id 0 | task 10618 | processing task, is_child = 0 2.47.506.716 I slot print_timing: id 0 | task 10618 | prompt eval time = 171.07 ms / 579 tokens ( 0.30 ms per token, 3384.66 tokens per second) 2.47.506.724 I slot print_timing: id 0 | task 10618 | eval time = 694.56 ms / 54 tokens ( 13.10 ms per token, 76.31 tokens per second) 2.47.506.725 I slot print_timing: id 0 | task 10618 | total time = 865.62 ms / 633 tokens 2.47.506.726 I slot print_timing: id 0 | task 10618 | graphs reused = 10169 2.47.506.727 I slot print_timing: id 0 | task 10618 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.506.769 I slot release: id 0 | task 10618 | stop processing: n_tokens = 657, truncated = 0 2.47.539.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 167410936 2.47.539.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.47.565.133 I slot launch_slot_: id 0 | task 10673 | processing task, is_child = 0 2.48.792.740 I slot print_timing: id 0 | task 10673 | prompt eval time = 264.95 ms / 919 tokens ( 0.29 ms per token, 3468.55 tokens per second) 2.48.792.745 I slot print_timing: id 0 | task 10673 | eval time = 962.64 ms / 73 tokens ( 13.37 ms per token, 74.79 tokens per second) 2.48.792.747 I slot print_timing: id 0 | task 10673 | total time = 1227.59 ms / 992 tokens 2.48.792.747 I slot print_timing: id 0 | task 10673 | graphs reused = 10240 2.48.792.748 I slot print_timing: id 0 | task 10673 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.792.798 I slot release: id 0 | task 10673 | stop processing: n_tokens = 1016, truncated = 0 2.48.817.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 168696965 2.48.818.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 2.48.823.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 2.48.861.577 I slot launch_slot_: id 0 | task 10747 | processing task, is_child = 0 2.49.604.045 I slot print_timing: id 0 | task 10747 | prompt eval time = 241.59 ms / 865 tokens ( 0.28 ms per token, 3580.48 tokens per second) 2.49.604.051 I slot print_timing: id 0 | task 10747 | eval time = 500.86 ms / 39 tokens ( 13.18 ms per token, 75.87 tokens per second) 2.49.604.052 I slot print_timing: id 0 | task 10747 | total time = 742.45 ms / 904 tokens 2.49.604.053 I slot print_timing: id 0 | task 10747 | graphs reused = 10277 2.49.604.054 I slot print_timing: id 0 | task 10747 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.604.100 I slot release: id 0 | task 10747 | stop processing: n_tokens = 928, truncated = 0 2.49.627.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 169508267 2.49.627.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 2.49.632.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 2.49.666.597 I slot launch_slot_: id 0 | task 10787 | processing task, is_child = 0 2.52.794.674 I slot print_timing: id 0 | task 10787 | n_gen = 231, tg = 76.57 t/s, tg_3s = 76.91 t/s 2.55.795.566 I slot print_timing: id 0 | task 10787 | n_gen = 461, tg = 76.61 t/s, tg_3s = 76.64 t/s 2.58.800.355 I slot print_timing: id 0 | task 10787 | n_gen = 690, tg = 76.48 t/s, tg_3s = 76.21 t/s 3.01.804.029 I slot print_timing: id 0 | task 10787 | n_gen = 917, tg = 76.25 t/s, tg_3s = 75.57 t/s 3.03.222.560 I slot print_timing: id 0 | task 10787 | prompt eval time = 124.40 ms / 408 tokens ( 0.30 ms per token, 3279.69 tokens per second) 3.03.222.566 I slot print_timing: id 0 | task 10787 | eval time = 13431.55 ms / 1024 tokens ( 13.13 ms per token, 76.16 tokens per second) 3.03.222.567 I slot print_timing: id 0 | task 10787 | total time = 13555.95 ms / 1432 tokens 3.03.222.568 I slot print_timing: id 0 | task 10787 | graphs reused = 11295 3.03.222.569 I slot print_timing: id 0 | task 10787 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.222.601 I slot release: id 0 | task 10787 | stop processing: n_tokens = 1456, truncated = 0 3.03.226.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1456, t_last = 183126767 3.03.226.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 3.03.231.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 3.03.284.372 I slot launch_slot_: id 0 | task 11812 | processing task, is_child = 0 3.05.197.452 I slot print_timing: id 0 | task 11812 | prompt eval time = 101.33 ms / 338 tokens ( 0.30 ms per token, 3335.73 tokens per second) 3.05.197.457 I slot print_timing: id 0 | task 11812 | eval time = 1811.74 ms / 141 tokens ( 12.94 ms per token, 77.27 tokens per second) 3.05.197.458 I slot print_timing: id 0 | task 11812 | total time = 1913.07 ms / 479 tokens 3.05.197.459 I slot print_timing: id 0 | task 11812 | graphs reused = 11434 3.05.197.460 I slot print_timing: id 0 | task 11812 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.197.488 I slot release: id 0 | task 11812 | stop processing: n_tokens = 505, truncated = 0 3.05.223.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 185101655 3.05.223.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 3.05.245.530 I slot launch_slot_: id 0 | task 11954 | processing task, is_child = 0 3.08.349.639 I slot print_timing: id 0 | task 11954 | n_gen = 232, tg = 76.94 t/s, tg_3s = 77.28 t/s 3.11.350.848 I slot print_timing: id 0 | task 11954 | n_gen = 462, tg = 76.79 t/s, tg_3s = 76.64 t/s 3.14.363.502 I slot print_timing: id 0 | task 11954 | n_gen = 692, tg = 76.64 t/s, tg_3s = 76.34 t/s 3.17.363.661 I slot print_timing: id 0 | task 11954 | n_gen = 919, tg = 76.40 t/s, tg_3s = 75.66 t/s 3.18.756.316 I slot print_timing: id 0 | task 11954 | prompt eval time = 101.87 ms / 363 tokens ( 0.28 ms per token, 3563.37 tokens per second) 3.18.756.321 I slot print_timing: id 0 | task 11954 | eval time = 13408.90 ms / 1024 tokens ( 13.11 ms per token, 76.29 tokens per second) 3.18.756.322 I slot print_timing: id 0 | task 11954 | total time = 13510.77 ms / 1387 tokens 3.18.756.323 I slot print_timing: id 0 | task 11954 | graphs reused = 12452 3.18.756.324 I slot print_timing: id 0 | task 11954 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.756.353 I slot release: id 0 | task 11954 | stop processing: n_tokens = 1413, truncated = 0 3.18.780.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1413, t_last = 198660520 3.18.780.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 3.18.789.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 3.18.847.224 I slot launch_slot_: id 0 | task 12979 | processing task, is_child = 0 3.21.948.684 I slot print_timing: id 0 | task 12979 | n_gen = 233, tg = 77.09 t/s, tg_3s = 77.42 t/s 3.24.957.447 I slot print_timing: id 0 | task 12979 | n_gen = 464, tg = 76.93 t/s, tg_3s = 76.78 t/s 3.27.964.461 I slot print_timing: id 0 | task 12979 | n_gen = 694, tg = 76.79 t/s, tg_3s = 76.49 t/s 3.30.971.544 I slot print_timing: id 0 | task 12979 | n_gen = 922, tg = 76.54 t/s, tg_3s = 75.82 t/s 3.32.328.332 I slot print_timing: id 0 | task 12979 | prompt eval time = 92.03 ms / 317 tokens ( 0.29 ms per token, 3444.60 tokens per second) 3.32.328.337 I slot print_timing: id 0 | task 12979 | eval time = 13389.06 ms / 1024 tokens ( 13.09 ms per token, 76.41 tokens per second) 3.32.328.338 I slot print_timing: id 0 | task 12979 | total time = 13481.09 ms / 1341 tokens 3.32.328.339 I slot print_timing: id 0 | task 12979 | graphs reused = 13470 3.32.328.339 I slot print_timing: id 0 | task 12979 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.328.368 I slot release: id 0 | task 12979 | stop processing: n_tokens = 1367, truncated = 0 3.32.356.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1367, t_last = 212232534 3.32.356.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 3.32.363.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 3.32.414.869 I slot launch_slot_: id 0 | task 14004 | processing task, is_child = 0 3.35.546.708 I slot print_timing: id 0 | task 14004 | n_gen = 231, tg = 76.47 t/s, tg_3s = 76.80 t/s 3.37.858.021 I slot print_timing: id 0 | task 14004 | prompt eval time = 123.96 ms / 389 tokens ( 0.32 ms per token, 3138.03 tokens per second) 3.37.858.027 I slot print_timing: id 0 | task 14004 | eval time = 5319.17 ms / 408 tokens ( 13.07 ms per token, 76.52 tokens per second) 3.37.858.028 I slot print_timing: id 0 | task 14004 | total time = 5443.14 ms / 797 tokens 3.37.858.029 I slot print_timing: id 0 | task 14004 | graphs reused = 13874 3.37.858.029 I slot print_timing: id 0 | task 14004 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.858.060 I slot release: id 0 | task 14004 | stop processing: n_tokens = 821, truncated = 0 3.37.873.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 821, t_last = 217762227 3.37.873.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.101 MiB) 3.37.904.432 I slot launch_slot_: id 0 | task 14413 | processing task, is_child = 0 3.38.395.180 I slot print_timing: id 0 | task 14413 | prompt eval time = 91.13 ms / 300 tokens ( 0.30 ms per token, 3292.00 tokens per second) 3.38.395.185 I slot print_timing: id 0 | task 14413 | eval time = 399.60 ms / 31 tokens ( 13.32 ms per token, 75.07 tokens per second) 3.38.395.186 I slot print_timing: id 0 | task 14413 | total time = 490.73 ms / 331 tokens 3.38.395.187 I slot print_timing: id 0 | task 14413 | graphs reused = 13903 3.38.395.188 I slot print_timing: id 0 | task 14413 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.395.216 I slot release: id 0 | task 14413 | stop processing: n_tokens = 355, truncated = 0 3.38.420.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 218299383 3.38.420.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.071 MiB) 3.38.439.644 I slot launch_slot_: id 0 | task 14445 | processing task, is_child = 0 3.39.114.791 I slot print_timing: id 0 | task 14445 | prompt eval time = 101.97 ms / 341 tokens ( 0.30 ms per token, 3344.12 tokens per second) 3.39.114.796 I slot print_timing: id 0 | task 14445 | eval time = 573.16 ms / 45 tokens ( 13.03 ms per token, 76.77 tokens per second) 3.39.114.797 I slot print_timing: id 0 | task 14445 | total time = 675.13 ms / 386 tokens 3.39.114.798 I slot print_timing: id 0 | task 14445 | graphs reused = 13946 3.39.114.799 I slot print_timing: id 0 | task 14445 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.114.826 I slot release: id 0 | task 14445 | stop processing: n_tokens = 410, truncated = 0 3.39.135.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 219018993 3.39.135.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 3.39.157.792 I slot launch_slot_: id 0 | task 14491 | processing task, is_child = 0 3.41.062.457 I slot print_timing: id 0 | task 14491 | prompt eval time = 92.19 ms / 332 tokens ( 0.28 ms per token, 3601.38 tokens per second) 3.41.062.463 I slot print_timing: id 0 | task 14491 | eval time = 1812.46 ms / 141 tokens ( 12.95 ms per token, 77.24 tokens per second) 3.41.062.464 I slot print_timing: id 0 | task 14491 | total time = 1904.65 ms / 473 tokens 3.41.062.465 I slot print_timing: id 0 | task 14491 | graphs reused = 14085 3.41.062.466 I slot print_timing: id 0 | task 14491 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.062.493 I slot release: id 0 | task 14491 | stop processing: n_tokens = 497, truncated = 0 3.41.085.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 497, t_last = 220966660 3.41.102.161 I slot launch_slot_: id 0 | task 14633 | processing task, is_child = 0 3.42.002.837 I slot print_timing: id 0 | task 14633 | prompt eval time = 82.96 ms / 269 tokens ( 0.31 ms per token, 3242.68 tokens per second) 3.42.002.842 I slot print_timing: id 0 | task 14633 | eval time = 817.71 ms / 64 tokens ( 12.98 ms per token, 77.04 tokens per second) 3.42.002.843 I slot print_timing: id 0 | task 14633 | total time = 900.66 ms / 333 tokens 3.42.002.844 I slot print_timing: id 0 | task 14633 | graphs reused = 14147 3.42.002.845 I slot print_timing: id 0 | task 14633 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.002.870 I slot release: id 0 | task 14633 | stop processing: n_tokens = 357, truncated = 0 3.42.021.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 221907037 3.42.034.291 I slot launch_slot_: id 0 | task 14698 | processing task, is_child = 0 3.44.472.498 I slot print_timing: id 0 | task 14698 | prompt eval time = 101.33 ms / 341 tokens ( 0.30 ms per token, 3365.28 tokens per second) 3.44.472.503 I slot print_timing: id 0 | task 14698 | eval time = 2336.86 ms / 181 tokens ( 12.98 ms per token, 77.03 tokens per second) 3.44.472.504 I slot print_timing: id 0 | task 14698 | total time = 2438.19 ms / 522 tokens 3.44.472.505 I slot print_timing: id 0 | task 14698 | graphs reused = 14325 3.44.472.506 I slot print_timing: id 0 | task 14698 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.472.536 I slot release: id 0 | task 14698 | stop processing: n_tokens = 546, truncated = 0 3.44.492.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 224376703 3.44.492.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 3.44.518.282 I slot launch_slot_: id 0 | task 14880 | processing task, is_child = 0 3.46.761.082 I slot print_timing: id 0 | task 14880 | prompt eval time = 101.25 ms / 343 tokens ( 0.30 ms per token, 3387.59 tokens per second) 3.46.761.087 I slot print_timing: id 0 | task 14880 | eval time = 2141.53 ms / 166 tokens ( 12.98 ms per token, 77.05 tokens per second) 3.46.761.088 I slot print_timing: id 0 | task 14880 | total time = 2242.78 ms / 509 tokens 3.46.761.089 I slot print_timing: id 0 | task 14880 | graphs reused = 14488 3.46.761.090 I slot print_timing: id 0 | task 14880 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.761.118 I slot release: id 0 | task 14880 | stop processing: n_tokens = 533, truncated = 0 3.46.782.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 226665284 3.46.782.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 3.46.806.611 I slot launch_slot_: id 0 | task 15047 | processing task, is_child = 0 3.49.920.678 I slot print_timing: id 0 | task 15047 | n_gen = 233, tg = 77.01 t/s, tg_3s = 77.35 t/s 3.52.931.584 I slot print_timing: id 0 | task 15047 | n_gen = 464, tg = 76.87 t/s, tg_3s = 76.72 t/s 3.55.943.898 I slot print_timing: id 0 | task 15047 | n_gen = 694, tg = 76.70 t/s, tg_3s = 76.35 t/s 3.57.474.080 I slot print_timing: id 0 | task 15047 | prompt eval time = 101.65 ms / 347 tokens ( 0.29 ms per token, 3413.78 tokens per second) 3.57.474.085 I slot print_timing: id 0 | task 15047 | eval time = 10565.81 ms / 810 tokens ( 13.06 ms per token, 76.57 tokens per second) 3.57.474.086 I slot print_timing: id 0 | task 15047 | total time = 10667.45 ms / 1157 tokens 3.57.474.087 I slot print_timing: id 0 | task 15047 | graphs reused = 15293 3.57.474.088 I slot print_timing: id 0 | task 15047 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.474.117 I slot release: id 0 | task 15047 | stop processing: n_tokens = 1181, truncated = 0 3.57.488.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1181, t_last = 237378284 3.57.488.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 3.57.493.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 3.57.541.233 I slot launch_slot_: id 0 | task 15858 | processing task, is_child = 0 4.00.646.004 I slot print_timing: id 0 | task 15858 | n_gen = 233, tg = 77.01 t/s, tg_3s = 77.34 t/s 4.03.656.120 I slot print_timing: id 0 | task 15858 | n_gen = 464, tg = 76.88 t/s, tg_3s = 76.74 t/s 4.06.663.340 I slot print_timing: id 0 | task 15858 | n_gen = 694, tg = 76.74 t/s, tg_3s = 76.48 t/s 4.09.669.320 I slot print_timing: id 0 | task 15858 | n_gen = 922, tg = 76.52 t/s, tg_3s = 75.85 t/s 4.11.025.927 I slot print_timing: id 0 | task 15858 | prompt eval time = 92.17 ms / 332 tokens ( 0.28 ms per token, 3601.96 tokens per second) 4.11.025.933 I slot print_timing: id 0 | task 15858 | eval time = 13392.50 ms / 1024 tokens ( 13.09 ms per token, 76.39 tokens per second) 4.11.025.935 I slot print_timing: id 0 | task 15858 | total time = 13484.68 ms / 1356 tokens 4.11.025.936 I slot print_timing: id 0 | task 15858 | graphs reused = 16311 4.11.025.938 I slot print_timing: id 0 | task 15858 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.025.969 I slot release: id 0 | task 15858 | stop processing: n_tokens = 1380, truncated = 0 4.11.051.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1380, t_last = 250930136 4.11.052.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 4.11.057.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 4.11.109.627 I slot launch_slot_: id 0 | task 16883 | processing task, is_child = 0 4.11.710.150 I slot print_timing: id 0 | task 16883 | prompt eval time = 92.50 ms / 332 tokens ( 0.28 ms per token, 3589.34 tokens per second) 4.11.710.156 I slot print_timing: id 0 | task 16883 | eval time = 508.01 ms / 40 tokens ( 13.03 ms per token, 76.77 tokens per second) 4.11.710.157 I slot print_timing: id 0 | task 16883 | total time = 600.50 ms / 372 tokens 4.11.710.158 I slot print_timing: id 0 | task 16883 | graphs reused = 16349 4.11.710.159 I slot print_timing: id 0 | task 16883 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.710.187 I slot release: id 0 | task 16883 | stop processing: n_tokens = 396, truncated = 0 4.11.738.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 251614353 4.11.738.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 4.11.758.261 I slot launch_slot_: id 0 | task 16924 | processing task, is_child = 0 4.13.582.640 I slot print_timing: id 0 | task 16924 | prompt eval time = 101.87 ms / 354 tokens ( 0.29 ms per token, 3475.12 tokens per second) 4.13.582.646 I slot print_timing: id 0 | task 16924 | eval time = 1722.50 ms / 133 tokens ( 13.05 ms per token, 76.63 tokens per second) 4.13.582.648 I slot print_timing: id 0 | task 16924 | total time = 1824.37 ms / 487 tokens 4.13.582.648 I slot print_timing: id 0 | task 16924 | graphs reused = 16480 4.13.582.649 I slot print_timing: id 0 | task 16924 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.582.679 I slot release: id 0 | task 16924 | stop processing: n_tokens = 511, truncated = 0 4.13.604.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 253486846 4.13.604.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 4.13.630.429 I slot launch_slot_: id 0 | task 17058 | processing task, is_child = 0 4.16.736.620 I slot print_timing: id 0 | task 17058 | n_gen = 232, tg = 76.90 t/s, tg_3s = 77.24 t/s 4.17.088.331 I slot print_timing: id 0 | task 17058 | prompt eval time = 102.46 ms / 354 tokens ( 0.29 ms per token, 3455.04 tokens per second) 4.17.088.336 I slot print_timing: id 0 | task 17058 | eval time = 3355.43 ms / 259 tokens ( 13.01 ms per token, 76.89 tokens per second) 4.17.088.337 I slot print_timing: id 0 | task 17058 | total time = 3457.89 ms / 613 tokens 4.17.088.338 I slot print_timing: id 0 | task 17058 | graphs reused = 16736 4.17.088.339 I slot print_timing: id 0 | task 17058 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.088.370 I slot release: id 0 | task 17058 | stop processing: n_tokens = 637, truncated = 0 4.17.092.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 256992537 4.17.113.330 I slot launch_slot_: id 0 | task 17318 | processing task, is_child = 0 4.17.995.478 I slot print_timing: id 0 | task 17318 | prompt eval time = 101.11 ms / 339 tokens ( 0.30 ms per token, 3352.65 tokens per second) 4.17.995.484 I slot print_timing: id 0 | task 17318 | eval time = 781.02 ms / 61 tokens ( 13.02 ms per token, 76.82 tokens per second) 4.17.995.485 I slot print_timing: id 0 | task 17318 | total time = 882.13 ms / 400 tokens 4.17.995.486 I slot print_timing: id 0 | task 17318 | graphs reused = 16795 4.17.995.486 I slot print_timing: id 0 | task 17318 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.995.515 I slot release: id 0 | task 17318 | stop processing: n_tokens = 424, truncated = 0 4.18.009.605 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 257899682 4.18.009.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 4.18.030.956 I slot launch_slot_: id 0 | task 17380 | processing task, is_child = 0 4.21.135.656 I slot print_timing: id 0 | task 17380 | n_gen = 232, tg = 76.92 t/s, tg_3s = 77.25 t/s 4.24.142.983 I slot print_timing: id 0 | task 17380 | n_gen = 462, tg = 76.70 t/s, tg_3s = 76.48 t/s 4.27.154.351 I slot print_timing: id 0 | task 17380 | n_gen = 692, tg = 76.59 t/s, tg_3s = 76.38 t/s 4.30.006.362 I slot print_timing: id 0 | task 17380 | prompt eval time = 101.63 ms / 351 tokens ( 0.29 ms per token, 3453.57 tokens per second) 4.30.006.368 I slot print_timing: id 0 | task 17380 | eval time = 11873.75 ms / 908 tokens ( 13.09 ms per token, 76.39 tokens per second) 4.30.006.369 I slot print_timing: id 0 | task 17380 | total time = 11975.39 ms / 1259 tokens 4.30.006.370 I slot print_timing: id 0 | task 17380 | graphs reused = 17697 4.30.006.371 I slot print_timing: id 0 | task 17380 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.006.400 I slot release: id 0 | task 17380 | stop processing: n_tokens = 1283, truncated = 0 4.30.028.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1283, t_last = 269910567 4.30.028.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.759 MiB) 4.30.035.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 4.30.082.545 I slot launch_slot_: id 0 | task 18289 | processing task, is_child = 0 4.32.038.946 I slot print_timing: id 0 | task 18289 | prompt eval time = 92.06 ms / 325 tokens ( 0.28 ms per token, 3530.31 tokens per second) 4.32.038.952 I slot print_timing: id 0 | task 18289 | eval time = 1864.33 ms / 145 tokens ( 12.95 ms per token, 77.24 tokens per second) 4.32.038.953 I slot print_timing: id 0 | task 18289 | total time = 1956.39 ms / 470 tokens 4.32.038.954 I slot print_timing: id 0 | task 18289 | graphs reused = 17840 4.32.038.955 I slot print_timing: id 0 | task 18289 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.038.982 I slot release: id 0 | task 18289 | stop processing: n_tokens = 494, truncated = 0 4.32.053.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 271943149 4.32.053.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 4.32.077.286 I slot launch_slot_: id 0 | task 18435 | processing task, is_child = 0 4.32.891.958 I slot print_timing: id 0 | task 18435 | prompt eval time = 91.35 ms / 308 tokens ( 0.30 ms per token, 3371.61 tokens per second) 4.32.891.963 I slot print_timing: id 0 | task 18435 | eval time = 723.31 ms / 56 tokens ( 13.15 ms per token, 76.04 tokens per second) 4.32.891.964 I slot print_timing: id 0 | task 18435 | total time = 814.66 ms / 364 tokens 4.32.891.965 I slot print_timing: id 0 | task 18435 | graphs reused = 17894 4.32.891.966 I slot print_timing: id 0 | task 18435 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.891.992 I slot release: id 0 | task 18435 | stop processing: n_tokens = 388, truncated = 0 4.32.907.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 272796159 4.32.920.809 I slot launch_slot_: id 0 | task 18492 | processing task, is_child = 0 4.36.023.064 I slot print_timing: id 0 | task 18492 | n_gen = 232, tg = 76.99 t/s, tg_3s = 77.32 t/s 4.36.699.150 I slot print_timing: id 0 | task 18492 | prompt eval time = 101.71 ms / 349 tokens ( 0.29 ms per token, 3431.22 tokens per second) 4.36.699.156 I slot print_timing: id 0 | task 18492 | eval time = 3676.61 ms / 284 tokens ( 12.99 ms per token, 76.97 tokens per second) 4.36.699.157 I slot print_timing: id 0 | task 18492 | total time = 3778.32 ms / 633 tokens 4.36.699.158 I slot print_timing: id 0 | task 18492 | graphs reused = 18175 4.36.699.159 I slot print_timing: id 0 | task 18492 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.699.189 I slot release: id 0 | task 18492 | stop processing: n_tokens = 657, truncated = 0 4.36.724.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 276603356 4.36.724.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.918 MiB) 4.36.755.059 I slot launch_slot_: id 0 | task 18777 | processing task, is_child = 0 4.38.009.397 I slot print_timing: id 0 | task 18777 | prompt eval time = 101.31 ms / 371 tokens ( 0.27 ms per token, 3662.06 tokens per second) 4.38.009.403 I slot print_timing: id 0 | task 18777 | eval time = 1153.01 ms / 90 tokens ( 12.96 ms per token, 77.19 tokens per second) 4.38.009.404 I slot print_timing: id 0 | task 18777 | total time = 1254.32 ms / 461 tokens 4.38.009.405 I slot print_timing: id 0 | task 18777 | graphs reused = 18263 4.38.009.405 I slot print_timing: id 0 | task 18777 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.009.435 I slot release: id 0 | task 18777 | stop processing: n_tokens = 490, truncated = 0 4.38.036.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 277913601 4.38.052.662 I slot launch_slot_: id 0 | task 18868 | processing task, is_child = 0 4.39.801.645 I slot print_timing: id 0 | task 18868 | prompt eval time = 91.53 ms / 303 tokens ( 0.30 ms per token, 3310.32 tokens per second) 4.39.801.651 I slot print_timing: id 0 | task 18868 | eval time = 1657.44 ms / 129 tokens ( 12.95 ms per token, 77.23 tokens per second) 4.39.801.652 I slot print_timing: id 0 | task 18868 | total time = 1748.97 ms / 432 tokens 4.39.801.653 I slot print_timing: id 0 | task 18868 | graphs reused = 18390 4.39.801.653 I slot print_timing: id 0 | task 18868 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.801.680 I slot release: id 0 | task 18868 | stop processing: n_tokens = 456, truncated = 0 4.39.826.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 279705847 4.39.826.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.423 MiB) 4.39.855.921 I slot launch_slot_: id 0 | task 18998 | processing task, is_child = 0 4.42.957.698 I slot print_timing: id 0 | task 18998 | n_gen = 233, tg = 77.06 t/s, tg_3s = 77.40 t/s 4.45.838.523 I slot print_timing: id 0 | task 18998 | prompt eval time = 91.24 ms / 312 tokens ( 0.29 ms per token, 3419.59 tokens per second) 4.45.838.529 I slot print_timing: id 0 | task 18998 | eval time = 5891.35 ms / 454 tokens ( 13.01 ms per token, 76.89 tokens per second) 4.45.838.530 I slot print_timing: id 0 | task 18998 | total time = 5982.58 ms / 766 tokens 4.45.838.531 I slot print_timing: id 0 | task 18998 | graphs reused = 18840 4.45.838.532 I slot print_timing: id 0 | task 18998 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.838.562 I slot release: id 0 | task 18998 | stop processing: n_tokens = 790, truncated = 0 4.45.842.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 285742729 4.45.868.057 I slot launch_slot_: id 0 | task 19453 | processing task, is_child = 0 4.47.771.846 I slot print_timing: id 0 | task 19453 | prompt eval time = 91.75 ms / 311 tokens ( 0.30 ms per token, 3389.83 tokens per second) 4.47.771.852 I slot print_timing: id 0 | task 19453 | eval time = 1812.03 ms / 141 tokens ( 12.94 ms per token, 77.26 tokens per second) 4.47.771.853 I slot print_timing: id 0 | task 19453 | total time = 1903.77 ms / 452 tokens 4.47.771.854 I slot print_timing: id 0 | task 19453 | graphs reused = 18979 4.47.771.855 I slot print_timing: id 0 | task 19453 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.771.881 I slot release: id 0 | task 19453 | stop processing: n_tokens = 476, truncated = 0 4.47.790.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 287676047 4.47.790.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 4.47.811.333 I slot launch_slot_: id 0 | task 19595 | processing task, is_child = 0 4.49.419.237 I slot print_timing: id 0 | task 19595 | prompt eval time = 92.22 ms / 331 tokens ( 0.28 ms per token, 3589.32 tokens per second) 4.49.419.242 I slot print_timing: id 0 | task 19595 | eval time = 1515.67 ms / 118 tokens ( 12.95 ms per token, 77.19 tokens per second) 4.49.419.243 I slot print_timing: id 0 | task 19595 | total time = 1607.89 ms / 449 tokens 4.49.419.244 I slot print_timing: id 0 | task 19595 | graphs reused = 19095 4.49.419.245 I slot print_timing: id 0 | task 19595 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.419.273 I slot release: id 0 | task 19595 | stop processing: n_tokens = 473, truncated = 0 4.49.423.265 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 473, t_last = 289323440 4.49.423.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 4.49.444.503 I slot launch_slot_: id 0 | task 19714 | processing task, is_child = 0 4.51.012.980 I slot print_timing: id 0 | task 19714 | prompt eval time = 92.35 ms / 335 tokens ( 0.28 ms per token, 3627.54 tokens per second) 4.51.012.985 I slot print_timing: id 0 | task 19714 | eval time = 1476.11 ms / 115 tokens ( 12.95 ms per token, 77.23 tokens per second) 4.51.012.986 I slot print_timing: id 0 | task 19714 | total time = 1568.46 ms / 450 tokens 4.51.012.987 I slot print_timing: id 0 | task 19714 | graphs reused = 19208 4.51.012.989 I slot print_timing: id 0 | task 19714 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.013.018 I slot release: id 0 | task 19714 | stop processing: n_tokens = 474, truncated = 0 4.51.035.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 290917185 4.51.035.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 4.51.055.835 I slot launch_slot_: id 0 | task 19830 | processing task, is_child = 0 4.51.578.476 I slot print_timing: id 0 | task 19830 | prompt eval time = 92.03 ms / 331 tokens ( 0.28 ms per token, 3596.69 tokens per second) 4.51.578.482 I slot print_timing: id 0 | task 19830 | eval time = 430.60 ms / 34 tokens ( 13.05 ms per token, 76.64 tokens per second) 4.51.578.483 I slot print_timing: id 0 | task 19830 | total time = 522.62 ms / 365 tokens 4.51.578.483 I slot print_timing: id 0 | task 19830 | graphs reused = 19240 4.51.578.484 I slot print_timing: id 0 | task 19830 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.578.511 I slot release: id 0 | task 19830 | stop processing: n_tokens = 389, truncated = 0 4.51.595.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 291482678 4.51.595.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 4.51.613.979 I slot launch_slot_: id 0 | task 19865 | processing task, is_child = 0 4.53.510.769 I slot print_timing: id 0 | task 19865 | prompt eval time = 92.00 ms / 328 tokens ( 0.28 ms per token, 3565.06 tokens per second) 4.53.510.774 I slot print_timing: id 0 | task 19865 | eval time = 1804.77 ms / 139 tokens ( 13.08 ms per token, 76.46 tokens per second) 4.53.510.775 I slot print_timing: id 0 | task 19865 | total time = 1896.77 ms / 467 tokens 4.53.510.776 I slot print_timing: id 0 | task 19865 | graphs reused = 19377 4.53.510.777 I slot print_timing: id 0 | task 19865 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.510.806 I slot release: id 0 | task 19865 | stop processing: n_tokens = 491, truncated = 0 4.53.534.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 293414973 4.53.534.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 4.53.555.946 I slot launch_slot_: id 0 | task 20005 | processing task, is_child = 0 4.56.076.017 I slot print_timing: id 0 | task 20005 | prompt eval time = 92.18 ms / 331 tokens ( 0.28 ms per token, 3590.68 tokens per second) 4.56.076.024 I slot print_timing: id 0 | task 20005 | eval time = 2427.87 ms / 186 tokens ( 13.12 ms per token, 76.20 tokens per second) 4.56.076.025 I slot print_timing: id 0 | task 20005 | total time = 2520.05 ms / 517 tokens 4.56.076.026 I slot print_timing: id 0 | task 20005 | graphs reused = 19560 4.56.076.027 I slot print_timing: id 0 | task 20005 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.076.058 I slot release: id 0 | task 20005 | stop processing: n_tokens = 541, truncated = 0 4.56.092.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 295980225 4.56.092.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 4.56.117.930 I slot launch_slot_: id 0 | task 20192 | processing task, is_child = 0 4.56.909.266 I slot print_timing: id 0 | task 20192 | prompt eval time = 101.89 ms / 348 tokens ( 0.29 ms per token, 3415.31 tokens per second) 4.56.909.272 I slot print_timing: id 0 | task 20192 | eval time = 689.42 ms / 54 tokens ( 13.01 ms per token, 76.88 tokens per second) 4.56.909.273 I slot print_timing: id 0 | task 20192 | total time = 791.32 ms / 402 tokens 4.56.909.274 I slot print_timing: id 0 | task 20192 | graphs reused = 19612 4.56.909.274 I slot print_timing: id 0 | task 20192 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.909.303 I slot release: id 0 | task 20192 | stop processing: n_tokens = 426, truncated = 0 4.56.934.244 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 296813470 4.56.934.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 4.56.952.557 I slot launch_slot_: id 0 | task 20247 | processing task, is_child = 0 4.57.721.347 I slot print_timing: id 0 | task 20247 | prompt eval time = 92.33 ms / 332 tokens ( 0.28 ms per token, 3595.95 tokens per second) 4.57.721.352 I slot print_timing: id 0 | task 20247 | eval time = 676.45 ms / 53 tokens ( 13.01 ms per token, 76.87 tokens per second) 4.57.721.354 I slot print_timing: id 0 | task 20247 | total time = 768.77 ms / 385 tokens 4.57.721.354 I slot print_timing: id 0 | task 20247 | graphs reused = 19663 4.57.721.355 I slot print_timing: id 0 | task 20247 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.721.383 I slot release: id 0 | task 20247 | stop processing: n_tokens = 411, truncated = 0 4.57.746.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 297625550 4.57.746.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 4.57.765.133 I slot launch_slot_: id 0 | task 20301 | processing task, is_child = 0 4.59.945.860 I slot print_timing: id 0 | task 20301 | prompt eval time = 101.34 ms / 339 tokens ( 0.30 ms per token, 3345.21 tokens per second) 4.59.945.865 I slot print_timing: id 0 | task 20301 | eval time = 2079.37 ms / 161 tokens ( 13.00 ms per token, 76.95 tokens per second) 4.59.945.866 I slot print_timing: id 0 | task 20301 | total time = 2180.71 ms / 500 tokens 4.59.945.867 I slot print_timing: id 0 | task 20301 | graphs reused = 19821 4.59.945.868 I slot print_timing: id 0 | task 20301 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.945.900 I slot release: id 0 | task 20301 | stop processing: n_tokens = 524, truncated = 0 4.59.963.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 299850067 4.59.963.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 4.59.985.705 I slot launch_slot_: id 0 | task 20463 | processing task, is_child = 0 5.00.543.693 I slot print_timing: id 0 | task 20463 | prompt eval time = 101.34 ms / 343 tokens ( 0.30 ms per token, 3384.65 tokens per second) 5.00.543.698 I slot print_timing: id 0 | task 20463 | eval time = 456.63 ms / 36 tokens ( 13.05 ms per token, 76.65 tokens per second) 5.00.543.699 I slot print_timing: id 0 | task 20463 | total time = 557.97 ms / 379 tokens 5.00.543.700 I slot print_timing: id 0 | task 20463 | graphs reused = 19855 5.00.543.702 I slot print_timing: id 0 | task 20463 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.543.729 I slot release: id 0 | task 20463 | stop processing: n_tokens = 403, truncated = 0 5.00.569.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 300447896 5.00.569.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.945 MiB) 5.00.589.543 I slot launch_slot_: id 0 | task 20500 | processing task, is_child = 0 5.03.694.183 I slot print_timing: id 0 | task 20500 | n_gen = 232, tg = 76.93 t/s, tg_3s = 77.26 t/s 5.06.695.434 I slot print_timing: id 0 | task 20500 | n_gen = 462, tg = 76.78 t/s, tg_3s = 76.63 t/s 5.09.705.938 I slot print_timing: id 0 | task 20500 | n_gen = 690, tg = 76.43 t/s, tg_3s = 75.73 t/s 5.12.711.116 I slot print_timing: id 0 | task 20500 | n_gen = 917, tg = 76.21 t/s, tg_3s = 75.54 t/s 5.14.131.532 I slot print_timing: id 0 | task 20500 | prompt eval time = 101.79 ms / 360 tokens ( 0.28 ms per token, 3536.66 tokens per second) 5.14.131.538 I slot print_timing: id 0 | task 20500 | eval time = 13440.18 ms / 1024 tokens ( 13.14 ms per token, 76.12 tokens per second) 5.14.131.539 I slot print_timing: id 0 | task 20500 | total time = 13541.97 ms / 1384 tokens 5.14.131.540 I slot print_timing: id 0 | task 20500 | graphs reused = 20873 5.14.131.541 I slot print_timing: id 0 | task 20500 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.131.570 I slot release: id 0 | task 20500 | stop processing: n_tokens = 1408, truncated = 0 5.14.135.868 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1408, t_last = 314035737 5.14.135.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 5.14.140.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 5.14.190.660 I slot launch_slot_: id 0 | task 21525 | processing task, is_child = 0 5.14.903.951 I slot print_timing: id 0 | task 21525 | prompt eval time = 101.37 ms / 341 tokens ( 0.30 ms per token, 3364.05 tokens per second) 5.14.903.956 I slot print_timing: id 0 | task 21525 | eval time = 611.91 ms / 48 tokens ( 13.02 ms per token, 76.81 tokens per second) 5.14.903.957 I slot print_timing: id 0 | task 21525 | total time = 713.27 ms / 389 tokens 5.14.903.959 I slot print_timing: id 0 | task 21525 | graphs reused = 20919 5.14.903.960 I slot print_timing: id 0 | task 21525 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.903.989 I slot release: id 0 | task 21525 | stop processing: n_tokens = 413, truncated = 0 5.14.925.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 314808156 5.14.925.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 5.14.945.527 I slot launch_slot_: id 0 | task 21574 | processing task, is_child = 0 5.16.788.176 I slot print_timing: id 0 | task 21574 | prompt eval time = 101.70 ms / 358 tokens ( 0.28 ms per token, 3520.26 tokens per second) 5.16.788.181 I slot print_timing: id 0 | task 21574 | eval time = 1740.94 ms / 135 tokens ( 12.99 ms per token, 76.97 tokens per second) 5.16.788.183 I slot print_timing: id 0 | task 21574 | total time = 1842.64 ms / 493 tokens 5.16.788.184 I slot print_timing: id 0 | task 21574 | graphs reused = 21051 5.16.788.185 I slot print_timing: id 0 | task 21574 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.788.214 I slot release: id 0 | task 21574 | stop processing: n_tokens = 517, truncated = 0 5.16.805.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 316692381 5.16.805.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 5.16.827.335 I slot launch_slot_: id 0 | task 21710 | processing task, is_child = 0 5.17.805.347 I slot print_timing: id 0 | task 21710 | prompt eval time = 101.89 ms / 358 tokens ( 0.28 ms per token, 3513.63 tokens per second) 5.17.805.353 I slot print_timing: id 0 | task 21710 | eval time = 876.11 ms / 67 tokens ( 13.27 ms per token, 75.33 tokens per second) 5.17.805.354 I slot print_timing: id 0 | task 21710 | total time = 978.00 ms / 425 tokens 5.17.805.355 I slot print_timing: id 0 | task 21710 | graphs reused = 21116 5.17.805.356 I slot print_timing: id 0 | task 21710 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.805.383 I slot release: id 0 | task 21710 | stop processing: n_tokens = 452, truncated = 0 5.17.833.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 317709549 5.17.833.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.976 MiB) 5.17.854.224 I slot launch_slot_: id 0 | task 21778 | processing task, is_child = 0 5.20.023.637 I slot print_timing: id 0 | task 21778 | prompt eval time = 124.08 ms / 387 tokens ( 0.32 ms per token, 3119.08 tokens per second) 5.20.023.643 I slot print_timing: id 0 | task 21778 | eval time = 2045.33 ms / 158 tokens ( 13.03 ms per token, 76.76 tokens per second) 5.20.023.645 I slot print_timing: id 0 | task 21778 | total time = 2169.40 ms / 545 tokens 5.20.023.646 I slot print_timing: id 0 | task 21778 | graphs reused = 21271 5.20.023.647 I slot print_timing: id 0 | task 21778 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.023.675 I slot release: id 0 | task 21778 | stop processing: n_tokens = 569, truncated = 0 5.20.050.842 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 319927842 5.20.050.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.694 MiB) 5.20.074.671 I slot launch_slot_: id 0 | task 21937 | processing task, is_child = 0 5.20.955.383 I slot print_timing: id 0 | task 21937 | prompt eval time = 92.33 ms / 333 tokens ( 0.28 ms per token, 3606.75 tokens per second) 5.20.955.389 I slot print_timing: id 0 | task 21937 | eval time = 788.36 ms / 61 tokens ( 13.14 ms per token, 76.11 tokens per second) 5.20.955.390 I slot print_timing: id 0 | task 21937 | total time = 880.69 ms / 394 tokens 5.20.955.391 I slot print_timing: id 0 | task 21937 | graphs reused = 21330 5.20.955.392 I slot print_timing: id 0 | task 21937 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.955.418 I slot release: id 0 | task 21937 | stop processing: n_tokens = 418, truncated = 0